id
int64 393k
2.82B
| repo
stringclasses 68
values | title
stringlengths 1
936
| body
stringlengths 0
256k
⌀ | labels
stringlengths 2
508
| priority
stringclasses 3
values | severity
stringclasses 3
values |
|---|---|---|---|---|---|---|
2,764,653,228 | ollama | mistral-nemo - context window 1024000? | ### What is the issue?
model_name='mistral-nemo'
ollama.show(model_name)['modelinfo']
{'general.architecture': 'llama',
'general.basename': 'Mistral-Nemo',
'general.file_type': 2,
'general.finetune': 'Instruct',
'general.languages': ['en', 'fr', 'de', 'es', 'it', 'pt', 'ru', 'zh', 'ja'],
'general.license': 'apache-2.0',
'general.parameter_count': 12247782400,
'general.quantization_version': 2,
'general.size_label': '12B',
'general.type': 'model',
'general.version': '2407',
'llama.attention.head_count': 32,
'llama.attention.head_count_kv': 8,
'llama.attention.key_length': 128,
'llama.attention.layer_norm_rms_epsilon': 1e-05,
'llama.attention.value_length': 128,
'llama.block_count': 40,
'llama.context_length': 1024000, <<<<<
'llama.embedding_length': 5120,
'llama.feed_forward_length': 14336,
'llama.rope.dimension_count': 128,
'llama.rope.freq_base': 1000000,
'llama.vocab_size': 131072,
'tokenizer.ggml.add_bos_token': True,
'tokenizer.ggml.add_eos_token': False,
'tokenizer.ggml.add_space_prefix': False,
'tokenizer.ggml.bos_token_id': 1,
'tokenizer.ggml.eos_token_id': 2,
'tokenizer.ggml.merges': None,
'tokenizer.ggml.model': 'gpt2',
'tokenizer.ggml.pre': 'tekken',
'tokenizer.ggml.token_type': None,
'tokenizer.ggml.tokens': None,
'tokenizer.ggml.unknown_token_id': 0}
Shouldn't it be 128k instead of 1M+?
### OS
Windows
### GPU
Nvidia
### CPU
Intel
### Ollama version
0.5.4 | bug | low | Minor |
2,764,661,443 | transformers | Unknown quantization type, got fp8 | ### System Info
- `transformers` version: 4.47.1
- Platform: macOS-15.1.1-arm64-arm-64bit
- Python version: 3.10.16
- Huggingface_hub version: 0.27.0
- Safetensors version: 0.4.5
- Accelerate version: 1.2.1
- Accelerate config: not found
- PyTorch version (GPU?): 2.5.1 (False)
- Tensorflow version (GPU?): not installed (NA)
- Flax version (CPU?/GPU?/TPU?): not installed (NA)
- Jax version: not installed
- JaxLib version: not installed
### Who can help?
@SunMarc @MekkCyber
### Information
- [ ] The official example scripts
- [X] My own modified scripts
### Tasks
- [ ] An officially supported task in the `examples` folder (such as GLUE/SQuAD, ...)
- [X] My own task or dataset (give details below)
### Reproduction
Issue arises when using AutoModelForCasualLM.from_pretrained()
The model used is `"deepseek-ai/DeepSeek-V3"`
File "/Users/ruidazeng/Demo/chatbot.py", line 13, in init
self.model = AutoModelForCausalLM.from_pretrained(
File "/opt/anaconda3/envs/gaming-bot/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py", line 559, in from_pretrained
return model_class.from_pretrained(
File "/opt/anaconda3/envs/gaming-bot/lib/python3.10/site-packages/transformers/modeling_utils.py", line 3659, in from_pretrained
config.quantization_config = AutoHfQuantizer.merge_quantization_configs(
File "/opt/anaconda3/envs/gaming-bot/lib/python3.10/site-packages/transformers/quantizers/auto.py", line 173, in merge_quantization_configs
quantization_config = AutoQuantizationConfig.from_dict(quantization_config)
File "/opt/anaconda3/envs/gaming-bot/lib/python3.10/site-packages/transformers/quantizers/auto.py", line 97, in from_dict
raise ValueError(
ValueError: Unknown quantization type, got fp8 - supported types are: ['awq', 'bitsandbytes_4bit', 'bitsandbytes_8bit', 'gptq', 'aqlm', 'quanto', 'eetq', 'hqq', 'compressed-tensors', 'fbgemm_fp8', 'torchao', 'bitnet']
### Expected behavior
This starts working when I manually reverted back to transformers (4.37.2), which has better compatibility with newer quantization methods. | bug | low | Critical |
2,764,663,831 | pytorch | [Mac/M1] torch.compile() -- expm1 returns an inaccurate result compared to the interpreted version | ### 🐛 Describe the bug
Input:
```
davidino@davidino-mbp pytorch % cat /tmp/repro.py
import torch
class Model(torch.nn.Module):
def __init__(self):
super().__init__()
def forward(self, x):
x = torch.floor(x)
x = torch.angle(x)
x = torch.sin(x)
s = torch.positive(x)
return torch.expm1(x)
func = Model().to('cpu')
x = torch.tensor([ 0.7076383233070374, 0.2585877180099487, -0.1782233268022537,
-0.0771917924284935, -1.8218737840652466, -0.6442450284957886,
-1.0207887887954712, 0.7611123919487000, 0.9056779742240906,
1.7948490381240845])
pata = func(x.clone())
print(pata)
func1 = torch.compile(func, fullgraph=True)
tino = func1(x.clone())
print(tino)
print(torch.allclose(pata, tino, equal_nan=True))
print(torch.__version__)
```
Output:
```
davidino@davidino-mbp pytorch % python /tmp/repro.py
tensor([ 0.0000e+00, 0.0000e+00, -8.7423e-08, -8.7423e-08, -8.7423e-08,
-8.7423e-08, -8.7423e-08, 0.0000e+00, 0.0000e+00, 0.0000e+00])
tensor([ 0.0000e+00, 0.0000e+00, -5.9605e-08, -5.9605e-08, -5.9605e-08,
-5.9605e-08, -5.9605e-08, 0.0000e+00, 0.0000e+00, 0.0000e+00])
False
2.6.0a0+gitf3e5078
```
### Versions
Collecting environment information...
PyTorch version: 2.6.0a0+gitf3e5078
Is debug build: False
CUDA used to build PyTorch: None
ROCM used to build PyTorch: N/A
OS: macOS 15.1.1 (arm64)
GCC version: Could not collect
Clang version: 16.0.0 (clang-1600.0.26.4)
CMake version: version 3.27.8
Libc version: N/A
Python version: 3.12.7 | packaged by Anaconda, Inc. | (main, Oct 4 2024, 08:22:19) [Clang 14.0.6 ] (64-bit runtime)
Python platform: macOS-15.1.1-arm64-arm-64bit
Is CUDA available: False
CUDA runtime version: No CUDA
CUDA_MODULE_LOADING set to: N/A
GPU models and configuration: No CUDA
Nvidia driver version: No CUDA
cuDNN version: No CUDA
HIP runtime version: N/A
MIOpen runtime version: N/A
Is XNNPACK available: True
CPU:
Apple M1 Pro
Versions of relevant libraries:
[pip3] flake8==7.0.0
[pip3] mypy==1.11.2
[pip3] mypy-extensions==1.0.0
[pip3] numpy==1.26.4
[pip3] numpydoc==1.7.0
[pip3] optree==0.13.1
[pip3] torch==2.6.0a0+gitf3e5078
[conda] numpy 1.26.4 py312h7f4fdc5_0
[conda] numpy-base 1.26.4 py312he047099_0
[conda] numpydoc 1.7.0 py312hca03da5_0
[conda] optree 0.13.1 pypi_0 pypi
[conda] torch 2.6.0a0+gitf3e5078 dev_0 <develop>
cc @kulinseth @albanD @malfet @DenisVieriu97 @jhavukainen @chauhang @penguinwu | oncall: pt2,oncall: cpu inductor | low | Critical |
2,764,676,156 | godot | Internal Script Error: Opcode 0 (Please report) when using CACHE_MODE_IGNORE_DEEP with ResourceLoader.load() | ### Tested versions
Godot version: 4.3.stable
### System information
Godot v4.3.stable - Windows 10.0.26100 - GLES3 (Compatibility) - NVIDIA GeForce RTX 3060 (NVIDIA; 32.0.15.6636) - 12th Gen Intel(R) Core(TM) i7-12700F (20 Threads)
### Issue description
Got an internal script error Opcode 0 and it is requested that I report it so I'm reporting it. Here's the image.
### Steps to reproduce
Use ResourceLoader.load(..., CACHE_MODE_IGNORE_DEEP) to load the same Resource at least twice.
### Minimal reproduction project (MRP)
MRP attached
[opcode-0-bug.zip](https://github.com/user-attachments/files/18283798/opcode-0-bug.zip)
Update: it appears to be related to the cach_mode I was using with ResourceLoader. Loading the resource a second time causes the issue. My understanding is that my use case should be valid but correct me if I misunderstood. | bug,topic:gdscript,topic:editor | low | Critical |
2,764,683,043 | next.js | Static export with skipTrailingSlashRedirect results in invalid request paths for RSC payload .txt files | ### Link to the code that reproduces this issue
https://github.com/klittlepage/next-skip-trailing-slash-rsc-bug
### To Reproduce
1. `next build`
2. Serve the resulting `out` directory
3. Navigate to the site root and note failed requests for rsc text files, e.g., http://localhost:8000/fails.txt?_rsc=1ld0r
### Current vs. Expected behavior
The routes generated by [createFetch](https://github.com/vercel/next.js/blob/35acd7e1faae66feddeffe6362fae9fb5a5b1281/packages/next/src/client/components/router-reducer/fetch-server-response.ts#L249) should take `skipTrailingSlashRedirect` into account, e.g., `http://localhost:8000/fails/index.txt?_rsc=1ld0r`.
### Provide environment information
```bash
Node.js v20.18.0
Operating System:
Platform: darwin
Arch: arm64
Version: Darwin Kernel Version 24.1.0: Thu Oct 10 21:05:23 PDT 2024; root:xnu-11215.41.3~2/RELEASE_ARM64_T6031
Available memory (MB): 36864
Available CPU cores: 14
Binaries:
Node: 20.18.0
npm: 10.8.2
Yarn: N/A
pnpm: 9.15.0
Relevant Packages:
next: 15.1.1-canary.23 // Latest available version is detected (15.1.1-canary.23).
eslint-config-next: N/A
react: 19.0.0
react-dom: 19.0.0
typescript: 5.3.3
Next.js Config:
output: export
```
### Which area(s) are affected? (Select all that apply)
create-next-app, Navigation, Output (export/standalone), Pages Router, Runtime
### Which stage(s) are affected? (Select all that apply)
next build (local), Other (Deployed)
### Additional context
Related: https://github.com/vercel/next.js/issues/73427
The fix proposed by @yukiyokotani in https://github.com/vercel/next.js/pull/73912, in conjunction with the patch below, resolves the issue. NB: the patch is against: https://github.com/yukiyokotani/next.js/tree/fix-static-export-rsc-payload-path.
```patch
diff --git a/packages/next/src/client/components/router-reducer/fetch-server-response.ts b/packages/next/src/client/components/router-reducer/fetch-server-response.ts
index 02545c4ddb..7b25952dec 100644
--- a/packages/next/src/client/components/router-reducer/fetch-server-response.ts
+++ b/packages/next/src/client/components/router-reducer/fetch-server-response.ts
@@ -11,6 +11,8 @@ const { createFromReadableStream } = (
require('react-server-dom-webpack/client')
) as typeof import('react-server-dom-webpack/client')
const basePath = (process.env.__NEXT_ROUTER_BASEPATH as string) || ''
+const skipTrailingSlashRedirect =
+ (process.env.__NEXT_MANUAL_TRAILING_SLASH as boolean) ?? false
import type {
FlightRouterState,
@@ -230,7 +232,7 @@ export function createFetch(
if (process.env.NODE_ENV === 'production') {
if (process.env.__NEXT_CONFIG_OUTPUT === 'export') {
- if (fetchUrl.pathname === basePath) {
+ if (fetchUrl.pathname === basePath || skipTrailingSlashRedirect) {
fetchUrl.pathname += '/index.txt'
} else if (fetchUrl.pathname.endsWith('/')) {
fetchUrl.pathname += 'index.txt'
``` | create-next-app,Output (export/standalone),Navigation,Runtime,Pages Router | low | Critical |
2,764,685,152 | pytorch | Torch.sparse.mm failing gradient computation at half precision. | ### 🐛 Describe the bug
When using torch.autocast, torch.sparse.mm(sparse_csr_tensor, dense_tensor) fails on the gradient computation with an unhelpful error. Half precision matrix multiplication with csr tensors was completed here https://github.com/pytorch/pytorch/issues/41069.
Simple reproduction:
```
weight = torch.rand(5, 4, device = "cuda", dtype = torch.float32)
weight = (weight * (weight < 0.2)).to_sparse_csr().requires_grad_(True)
inp = torch.rand(4, 3, device = "cuda", dtype = torch.float32, requires_grad = False)
with torch.autocast("cuda", dtype = torch.float16, enabled = True):
loss = torch.sparse.mm(weight, inp).sum()
loss.backward()
```
```
RuntimeError: sampled_addmm: Expected mat1 and mat2 to have the same dtype, but got Half and Float
```
Furthermore, if one tries to convert to half precision manually like below, they receive:
```
weight = torch.rand(5, 4, device = "cuda", dtype = torch.float32)
weight = (weight * (weight < 0.2)).to_sparse_csr().requires_grad_(True).half()
inp = torch.rand(4, 3, device = "cuda", dtype = torch.float32, requires_grad = False).half()
loss = torch.sparse.mm(weight, inp).sum()
loss.backward()
```
```
RuntimeError: "sampled_addmm_out_sparse_csr" not implemented for 'Half'
```
### Versions
torch==2.6.0.dev20241231+cu124
and
torch==2.5.1 (with cu124)
cc @alexsamardzic @nikitaved @pearu @cpuhrsch @amjames @bhosmer @jcaip | module: sparse,triaged,module: half | low | Critical |
2,764,692,762 | go | x/tools/go/packages: overlay does not work properly with external module files | Consider:
```go
package main
import (
"fmt"
"golang.org/x/tools/go/packages"
)
func main() {
fmt.Println(run())
}
func run() error {
cfg := packages.Config{
Mode: packages.LoadSyntax,
Dir: ".",
Overlay: map[string][]byte{
"/home/mateusz/go/pkg/mod/golang.org/x/[email protected]/go/packages/nonExistent.go": []byte(`package packages; func TestFunc() {}`), // New file
"/home/mateusz/go/pkg/mod/golang.org/x/[email protected]/go/packages/doc.go": []byte(`package packages; func TestFunc2() {}`), // File exists, but overridden.
// File exists, but overridden, additional import (unicode/utf8).
"/home/mateusz/go/pkg/mod/golang.org/x/[email protected]/go/packages/loadmode_string.go": []byte(`// Copyright 2019 The Go Authors. All rights reserved.
// Use of this source code is governed by a BSD-style
// license that can be found in the LICENSE file.
package packages
import (
"fmt"
"strings"
"unicode/utf8"
)
func TestFunc3(r rune) []byte {
return utf8.AppendRune(nil, r)
}
var modes = [...]struct {
mode LoadMode
name string
}{
{NeedName, "NeedName"},
{NeedFiles, "NeedFiles"},
{NeedCompiledGoFiles, "NeedCompiledGoFiles"},
{NeedImports, "NeedImports"},
{NeedDeps, "NeedDeps"},
{NeedExportFile, "NeedExportFile"},
{NeedTypes, "NeedTypes"},
{NeedSyntax, "NeedSyntax"},
{NeedTypesInfo, "NeedTypesInfo"},
{NeedTypesSizes, "NeedTypesSizes"},
{NeedForTest, "NeedForTest"},
{NeedModule, "NeedModule"},
{NeedEmbedFiles, "NeedEmbedFiles"},
{NeedEmbedPatterns, "NeedEmbedPatterns"},
}
func (mode LoadMode) String() string {
if mode == 0 {
return "LoadMode(0)"
}
var out []string
// named bits
for _, item := range modes {
if (mode & item.mode) != 0 {
mode ^= item.mode
out = append(out, item.name)
}
}
// unnamed residue
if mode != 0 {
if out == nil {
return fmt.Sprintf("LoadMode(%#x)", int(mode))
}
out = append(out, fmt.Sprintf("%#x", int(mode)))
}
if len(out) == 1 {
return out[0]
}
return "(" + strings.Join(out, "|") + ")"
}
`),
},
}
pkgs, err := packages.Load(&cfg, "./test")
if err != nil {
return err
}
packages.PrintErrors(pkgs)
return nil
}
```
This program runs `packages.Load` on a `./test` package, with three overlay files on the `golang.org/x/tools/go/packages` package.
- `nonExistent.go` - File does not exist, so this is a new file with a new func `TestFunc`.
- `doc.go` - File already exists, it defines a new func `TestFunc2`.
- `loadmode_string.go` - File already exists, it defines a new func `TestFunc3` and imports `unicode/utf8` (this package is not imported without overlays).
The `./test` package contains following file:
```go
package main
import (
"golang.org/x/tools/go/packages"
)
func main() {
packages.TestFunc()
packages.TestFunc2()
packages.TestFunc3('a')
}
```
```bash
$ go run .
-: # golang.org/x/tools/go/packages
/tmp/gocommand-708375563/3-loadmode_string.go:10:2: could not import unicode/utf8 (open : no such file or directory)
/home/mateusz/go/pkg/mod/golang.org/x/[email protected]/go/packages/loadmode_string.go:10:2: could not import unicode/utf8 (no metadata for unicode/utf8)
/tmp/aa/test/test.go:8:11: undefined: packages.TestFunc
<nil>
```
So:
- It is not able to import `unicode/utf8` (probably `go list` does not return it to `go/packages`).
- Newly added files are ignored (`nonExistent.go`).
- Overlay works, but only for files that already exist.
Opened this issue, because i think that this behavior is wrong, it should either work without any error for the example above, or just ignore the overlay completely.
CC @matloob (per https://dev.golang.org/owners) @adonovan | NeedsInvestigation,Tools | low | Critical |
2,764,694,662 | rust | Tracking issue for RFC 3722: Explicit ABIs in `extern` | This is a tracking issue for:
- https://github.com/rust-lang/rfcs/pull/3722
The feature gate for the issue is `#![feature(explicit_extern_abis)]`.
### About tracking issues
Tracking issues are used to record the overall progress of implementation. They are also used as hubs connecting to other relevant issues, e.g., bugs or open design questions. A tracking issue is however *not* meant for large scale discussion, questions, or bug reports about a feature. Instead, open a dedicated issue for the specific matter and add the relevant feature gate label.
### Steps
- [x] Accept an RFC.
- https://github.com/rust-lang/rfcs/pull/3722
- [x] Add migration lint.
- https://github.com/rust-lang/rust/pull/132357
- [x] Make and FCP the change to warn-by-default in all editions.
- https://github.com/rust-lang/rust/pull/132397
- [ ] Make this a hard error in the next edition on nightly under a feature flag.
- Blocked on finalizing the name and timing of the next edition.
- https://github.com/rust-lang/rust/pull/135340
- [ ] Add documentation to the [dev guide][].
- See the [instructions][doc-guide].
- [ ] Add documentation to the [reference][].
- See the [instructions][reference-instructions].
- [ ] Add formatting for new syntax to the [style guide][].
- See the [nightly style procedure][].
- [ ] Stabilize on nightly on the next edition.
- See the [instructions][stabilization-instructions].
[dev guide]: https://github.com/rust-lang/rustc-dev-guide
[doc-guide]: https://rustc-dev-guide.rust-lang.org/stabilization_guide.html#documentation-prs
[edition guide]: https://github.com/rust-lang/edition-guide
[nightly style procedure]: https://github.com/rust-lang/style-team/blob/master/nightly-style-procedure.md
[reference]: https://github.com/rust-lang/reference
[reference-instructions]: https://github.com/rust-lang/reference/blob/master/CONTRIBUTING.md
[stabilization-instructions]: https://rustc-dev-guide.rust-lang.org/stabilization_guide.html#stabilization-pr
[style guide]: https://github.com/rust-lang/rust/tree/master/src/doc/style-guide
### Unresolved Questions
None.
### Related
TODO.
### Implementation history
TODO.
| T-lang,C-tracking-issue,F-explicit_extern_abis | low | Critical |
2,764,722,432 | vscode | [Accessibility, a11y] Color contrast ratio of tree view `description` text is 4.381:1 which is less than 4.5:1 | <!-- ⚠️⚠️ Do Not Delete This! bug_report_template ⚠️⚠️ -->
<!-- Please read our Rules of Conduct: https://opensource.microsoft.com/codeofconduct/ -->
<!-- 🕮 Read our guide about submitting issues: https://github.com/microsoft/vscode/wiki/Submitting-Bugs-and-Suggestions -->
<!-- 🔎 Search existing issues to avoid creating duplicates. -->
<!-- 🧪 Test using the latest Insiders build to see if your issue has already been fixed: https://code.visualstudio.com/insiders/ -->
<!-- 💡 Instead of creating your report here, use 'Report Issue' from the 'Help' menu in VS Code to pre-fill useful information. -->
<!-- 🔧 Launch with `code --disable-extensions` to check. -->
<!-- 🪓 If you answered No above, use 'Help: Start Extension Bisect' from Command Palette to try to identify the cause. -->
<!-- 📣 Issues caused by an extension need to be reported directly to the extension publisher. The 'Help > Report Issue' dialog can assist with this. -->
- VS Code Version: 1.97.0-insider
- OS: Windows
- Color Theme: Dark+ (Default Dark+)
This issue is being escalated from here: https://github.com/microsoft/vscode-azurefunctions/issues/4332
## Steps to Reproduce:
1. Install the Azure Resources extension `ms-azuretools.vscode-azureresourcegroups`
2. Click on the `Azure` tab
3. Observe the "`Remote`" description in the `Resources` tree view
## Actual:
Color contrast ratio of tree view's `description` text is 4.381:1 which is less than 4.5:1
## Expected:
Color contrast ratio of tree view's `description` text should be greater than or equal to 4.5:1
This should reproduce for any tree view description in default dark mode.
| bug,themes,accessibility | low | Critical |
2,764,723,451 | godot | Bug: MultiMesh uses_colors error vs use_colors property | ### Tested versions
4.3 dev
### System information
Godot v4.3.stable - Windows 10.0.22631 - GLES3 (Compatibility) - NVIDIA GeForce RTX 4050 Laptop GPU (NVIDIA; 32.0.15.6070) - Intel(R) Core(TM) Ultra 7 155H (22 Threads)
### Issue description
Keep getting an error message using colors because its looking for the wrong property.
Following this tutorial:
https://docs.godotengine.org/en/stable/classes/class_multimesh.html#class-multimesh-property-use-colors
```
E 0:00:04:0397 game.tscn::GDScript_a3sjo:43 @ _ready(): Condition "!multimesh->uses_colors" is true.
<C++ Source> drivers/gles3/storage/mesh_storage.cpp:1714 @ multimesh_instance_set_color()
<Stack Trace> game.tscn::GDScript_a3sjo:43 @ _ready()
```
### Steps to reproduce
Create multimesh and enable `use_colors` and then set instance colors.
### Minimal reproduction project (MRP)
Official tutorial does it if you just switch on `use_colors`
https://docs.godotengine.org/en/stable/classes/class_multimesh.html#class-multimesh-property-use-colors | topic:core,topic:rendering | low | Critical |
2,764,752,829 | material-ui | [docs] Update "Unstyled" sections to point to new Base UI package | ### Related page
https://mui.com/material-ui/react-select/#unstyled
### Kind of issue
Other
### Issue description
Material UI components with Base UI equivalents have an "Unstyled" section in their component docs to direct users to the latter if they need them. With mui/base-ui now replacing the older legacy package in the material-ui repo, these links and descriptions should be updated to point to the new library.
The only question is when to do it. ASAP? Or should it coincide with a later milestone for Base UI—beta or stable release?
**Search keywords**: unstyled, base ui, docs | docs,priority: important,package: base-ui | low | Major |
2,764,757,622 | godot | Mathf.SmoothStep summary description could be improved | I was using the summary description of SmoothStep to help me produce a smoother movement animation between two points, but it seems to work quite differently to how I'd expect it to. I was assuming that I'd use it the same way as Lerp but with a faster result at the beginning and slower at the end.
I can see the power in the method now (thanks kleonc for helping me get my head around how it works). It'd be nice for someone to update the description to better clarify it's use.
https://github.com/godotengine/godot/blob/2582793d408ade0b6ed42f913ae33e7da5fb9184/modules/mono/glue/GodotSharp/GodotSharp/Core/Mathf.cs#L1595-L1612 | enhancement,documentation,topic:dotnet | low | Major |
2,764,781,852 | rust | Include Stabilization version in the tracking issue template | ### Location
- Tracking issues
- RFCs
- Stabilization Issues
- Unstable book
- Compiler error messages
### Summary
In a CI build against my crate's declared MSRV, I get this build failure:
```
error[E0658]: lint reasons are experimental
--> webfinger-rs/src/types/rel.rs:6:1
|
6 | / #[nutype(derive(
7 | | Debug,
8 | | Display,
9 | | Clone,
... |
19 | | Eq,
20 | | ))]
| |___^
|
= note: see issue #54503 <https://github.com/rust-lang/rust/issues/54503> for more information
= note: this error originates in the attribute macro `nutype` (in Nightly builds, run with -Z macro-backtrace for more info)
```
The fix for this is to bump my MSRV, which I'm fine with doing. But the process for finding what version this feature was introduced in is convoluted and doesn't have any path from the error message. A good place for that information to live would the in the first comment of the tracking issue link. Adding the info to the RFC and stabilization issue would be nice too. The only place where this is recorded currently is the rust blog https://blog.rust-lang.org/2024/09/05/Rust-1.81.0.html#lint-reasons
Obviously this is just one case, but it's something I've seen happen a few times. The underlying goal of this issue is that the link to the tracking issue is not a dead end for fixing the issue, but instead contains enough information to fix immediately. | C-enhancement,A-docs,A-meta | low | Critical |
2,764,782,622 | godot | Texture2D's has_alpha() function returns false regardless of whether the image has an alpha channel | ### Tested versions
v4.3.stable.official [77dcf97d8]
v4.4.dev7.official [46c8f8c5c]
v4.2.2.stable.official [15073afe3]
v4.0.stable.official [92bee43ad]
### System information
Godot v4.3.stable - Windows 10.0.19045 - Vulkan (Forward+) - dedicated AMD Radeon RX 5700 XT (Advanced Micro Devices, Inc.; 32.0.12019.1028) - 12th Gen Intel(R) Core(TM) i5-12400F (12 Threads)
### Issue description
I'm using a script to determine whether the albedo texture has an alpha channel and then set the transparency mode of the material based on that.
I have a ```Texture2D``` that I can verify as having an alpha channel, because of the editor preview, and through viewing the channels individually in GIMP. However, when I call ```has_alpha()``` on it, the function still returns ```false``` when I expect it to return ```true```.
This issue happens regardless if the texture is ```.png``` or ```.webp```
### Steps to reproduce
1. Export a ```Texture2D``` variable from a script
2. Set the variable to an imported texture known to have an alpha channel
3. Use the script to call ```has_alpha()``` on the ```Texture2D``` variable
4. Inspect the return value which will erroneously be ```false```
### Minimal reproduction project (MRP)
[Alpha Detection Test.zip](https://github.com/user-attachments/files/18284212/Alpha.Detection.Test.zip)
| discussion,topic:core,documentation | low | Minor |
2,764,794,331 | go | proposal: sync/v2: new package | ### Proposal Details
The math/rand/v2 package has been successful. Let's consider another v2 package: sync/v2.
This is an update of #47657.
### Background
The current sync package provides `Map` and `Pool` types. These types were designed before Go supported generics. They work with values of type `any`.
Using `any` is not compile-time-type-safe. Nothing prevents using a key or value of any arbitrary type with a `sync.Map`. Nothing prevents storing a value of any arbitrary type into a `sync.Pool`. Go is in general a type-safe language. For all the reasons why Go map and slice types define the their key and element types, `sync.Map` and `sync.Pool` should as well.
Also, using `any` is inefficient. Converting a non-pointer value to `any` requires a memory allocation. This means that building a `sync.Map` with a key type of `string` requires an extra allocation for every value stored in the map. Storing a slice type in a `sync.Pool` requires an extra allocation.
These issues are easily avoided by changing `sync.Map` and `sync.Pool` to be generic types.
While we can't change `Map` and `Pool` to be generic in the current sync package because of compatibility concerns (see the discussion at #48287), we could consider adding new generic types to the existing sync package, as proposed at #47657. However, that will leave us with a confusing wart in the sync package that we can never remove. Having both `sync.Pool` and (say) `sync.PoolOf` is confusing. Deprecating `sync.Pool` still leaves us with a strange name for the replacement type.
Introducing a sync/v2 package will permit us to easily transition from the current package to a new package. It's true that future users will have to know to import "sync/v2" rather than "sync". However, few people write their own imports these days, and this transition is easily handled by goimports and similar tools.
### Proposal
In the sync/v2 package, the following types and functions will be the same as in the current sync package:
```Go
func OnceFunc(f func()) func()
func OnceValue[T any](f func() T) func() T
func OnceValues[T1, T2 any](f func() (T1, T2)) func() (T1, T2)
type Cond struct{ ... }
func NewCond(l Locker) *Cond
type Locker interface{ ... }
type Mutex struct{ ... }
type Once struct{ ... }
type RWMutex struct{ ... }
type WaitGroup struct{ ... }
```
The existing `Map` type will be replaced by a new type that takes two type parameters. Note that the original `Range` method is replaced with an `All` method that returns an iterator.
```Go
// Map is like a Go map[K]V but is safe for concurrent use
// by multiple goroutines without additional locking or coordination.
// ...and so forth
type Map[K comparable, V any] struct { ... }
// Load returns the value stored in the map for a key, or the zero value if no
// value is present.
// The ok result indicates whether value was found in the map.
func (m *Map[K, V]) Load(key K) (value V, ok bool)
// Store sets the value for a key.
func (m *Map[K, V]) Store(key K, value V)
// LoadOrStore returns the existing value for the key if present.
// Otherwise, it stores and returns the given value.
// The loaded result is true if the value was loaded, false if stored.
func (m *Map[K, V]) LoadOrStore(key K, value V) (actual V, loaded bool)
// LoadAndDelete deletes the value for a key, returning the previous value if any.
// The loaded result reports whether the key was present.
func (m *Map[K, V]) LoadAndDelete(key K) (value V, loaded bool)
// Delete deletes the value for a key.
func (m *Map[K, V]) Delete(key K)
// Swap swaps the value for a key and returns the previous value if any.
// The loaded result reports whether the key was present.
func (m *Map[K, V]) Swap(key K, value V) (previous V, loaded bool)
// CompareAndDelete deletes the entry for key if its value is equal to old.
// This panics if V is not a comparable type.
//
// If there is no current value for key in the map, CompareAndDelete
// returns false.
func (m *Map[K, V]) CompareAndDelete(key K, old V) (deleted bool)
// CompareAndSwap swaps the old and new values for key
// if the value stored in the map is equal to old.
// This panics if V is not a comparable type.
func (m *Map[K, V]) CompareAndSwap(key K, old, new V) (swapped bool)
// Clear deletes all the entries, resulting in an empty Map.
func (m *Map[K, V]) Clear()
// All returns an iterator over the keys and values in the map.
// ... and so forth
func (m *Map[K, V]) All() iter.Seq2[K, V]
// TODO: Consider Keys and Values methods that return iterators, like maps.Keys and maps.Values.
```
The existing `Pool` type will be replaced by a new type that takes a type parameter.
2025-01-04: The new version of `Pool` does not have an exported `New` field; instead, use `NewPool` to create a `Pool` that calls a function to return new values.
~~Note that the original `Get` method is replaced by one that returns two results, with the second being a `bool` indicating whether a value was returned. This is only useful if the New field is optional: we could also change this to require the New field to be set, or to provide a default implementation that returns the zero value of `T`.~~
```Go
// A Pool is a set of temporary objects of type T that may be individually saved and retrieved.
// ...and so forth
type Pool[T any] struct {
...
}
// NewPool returns a new pool. If the newf argument is not nil, then when the pool is empty,
// newf is called to fetch a new value. This is useful when the values in the pool should be initialized.
func NewPool[T any] func(newf func() T) *Pool[T]
// Put adds x to the pool.
func (p *Pool[T]) Put(x T)
// Get selects an arbitrary item from the Pool, removes it from the
// Pool, and returns it to the caller.
// ...and so forth
//
// If Get does not have a value to return, and p was created with a call to [NewPool] with a non-nil argument,
// Get returns the result of calling the function passed to [NewPool].
func (p *Pool[T]) Get() T
``` | v2,Proposal | high | Critical |
2,764,810,294 | flutter | Triage process self-test | This is a test of our triage processes.
Please handle this issue the same way you would a normal valid but low-priority issue.
For more details see https://github.com/flutter/flutter/wiki/Triage | team-codelabs,team-infra,team-ecosystem,P2,team-release,team-news,team-android,triaged-android,triaged-codelabs,team-design,triaged-design,triaged-ecosystem,team-engine,triaged-engine,team-framework,triaged-framework,team-go_router,triaged-go_router,triaged-infra,team-ios,triaged-ios,team-tool,triaged-tool,team-web,triaged-web,team-games,triaged-games,team-text-input,triaged-text-input,team-macos,triaged-macos,team-windows,triaged-windows,team-linux,triaged-linux,team-accessibility,triaged-accessibility | low | Minor |
2,764,831,100 | neovim | C-c closes the command line window with multigrid | ### Problem
The commandline window is closed instead of just moving to the command line when pressing `C-c` with multigrid clients. This is especially bad when a popup window is visible, since the cursor will then also be placed in the wrong place.
### Steps to reproduce
1. launch an UI client with multigrid support, like Neovide `neovide -- --clean`
2. open the command line window `q:`
3. Press `C-c`
Observe that the command line window is closed
### Expected behavior
The cursor should move to the command line without closing the window.
### Nvim version (nvim -v)
NVIM v0.10.3
### Vim (not Nvim) behaves the same?
N/A
### Operating system/version
Linux
### Terminal name/version
Neovide 0.13.3
### $TERM environment variable
alacritty
### Installation
pacman | bug,ui,ui-extensibility,display,cmdline-mode | low | Minor |
2,764,907,652 | godot | CharacterBody2D position inconsistent across clients depending on collision layer mask | ### Tested versions
- Reproducible in v4.3.stable.official [77dcf97d8]
### System information
Windows 11 - v4.3.stable.official [77dcf97d8] - Forward+ - NVIDIA GeForce RTX 4070 Laptop GPU
### Issue description
I ran into an interesting bug with the CharacterBody2D physics and Networking. My simple example spawns the "Host" at 500,500 and the "Client" at 0,0. But then the client moves to 500,480 within a few frames.
### Example 1: Players have default collision layers
"Host" window has the "Client" player at 0,0 (as expected) but the "Client" window moves the player from 0,0 to 500,480.
Logged position changes:
```
Changed position (0, 0) (500, 500)
Changed position (0, 0) (0, -17.47415)
Changed position (0, -17.47415) (500, 480.2612)
Changed position (500, 480.2612) (500, 479.9677)
```
### Example 2: Players ignore other players
If the collision layer is changed to "2" (i.e. the players don't collide with each other) then the position of the "Client" is consistent.
It also is "fixed" by commenting out "move_and_slide();" on line 27 of "player.gd"
Thankfully, for my game I don't want the players to collide, so it it is good enough for me, but I would expect the "Client" player to be at 0,0 without changing the layer since the other player object is nowhere near (500,500).
### Steps to reproduce
1. Get the code from the attached project or clone the commit from my repro https://github.com/RyanRemer/multiplayer_1227/tree/ddef2c3baa4fc9119e5ce523030129106e95e9db
2. Run 2 instances of the game
3. Click "Host" on one and "Join" on the other
4. The "Client" player is at different positions on each window. On the "Host" they are at 0,0 but on the "Client" they are at 500, 479.9677.
Here is the log of any position changes:
```
Changed position (0, 0) (500, 500)
Changed position (0, 0) (0, -17.47415)
Changed position (0, -17.47415) (500, 480.2612)
Changed position (500, 480.2612) (500, 479.9677)
```
To "fix" it, change the Player > Collision > Layer to "2" instead of "1"
https://github.com/RyanRemer/multiplayer_1227/commit/d71a7cd2339b9cf879ca4d768d2a206757f6fda4
Of course, this has the side effect that players don't collide with each other
### Minimal reproduction project (MRP)
https://github.com/RyanRemer/multiplayer_1227/tree/ddef2c3baa4fc9119e5ce523030129106e95e9db
I also removed some other files to try and minimize the project here.
[project.zip](https://github.com/user-attachments/files/18284710/project.zip)
| bug,topic:physics,needs testing,topic:multiplayer | low | Critical |
2,764,930,500 | vscode | Allow to open multiple editors in one group by tab multiselect | <!-- ⚠️⚠️ Do Not Delete This! feature_request_template ⚠️⚠️ -->
<!-- Please read our Rules of Conduct: https://opensource.microsoft.com/codeofconduct/ -->
<!-- Please search existing issues to avoid creating duplicates. -->
<!-- Describe the feature you'd like. -->
currently am using this all the time with sublime ex.
which is very helpful when working with multiple files, so instead of reaching to the command palette, u just `shift + click` the tab u want to view side-by-side with the current opened editor.
i couldnt find an api to do this through an extension. | feature-request,workbench-tabs,workbench-editors | low | Minor |
2,764,932,907 | tauri | [bug] can not custom displayName localization for windows | ### Describe the bug
Currently, productName is used as the name of the app. On mac os, it is implemented by adding [lang].lproj/InfoPlist.strings. On Windows, I did not find the relevant implementation.
### Reproduction
_No response_
### Expected behavior
_No response_
### Full `tauri info` output
```text
。
```
### Stack trace
_No response_
### Additional context
_No response_ | type: bug,status: needs triage | low | Critical |
2,764,935,744 | yt-dlp | Add --download-archive option for YouTube playlists | ### DO NOT REMOVE OR SKIP THE ISSUE TEMPLATE
- [X] I understand that I will be **blocked** if I *intentionally* remove or skip any mandatory\* field
### Checklist
- [X] I'm requesting a site-specific feature
- [X] I've verified that I have **updated yt-dlp to nightly or master** ([update instructions](https://github.com/yt-dlp/yt-dlp#update-channels))
- [X] I've checked that all provided URLs are playable in a browser with the same IP and same login details
- [X] I've searched [known issues](https://github.com/yt-dlp/yt-dlp/issues/3766) and the [bugtracker](https://github.com/yt-dlp/yt-dlp/issues?q=) for similar issues **including closed ones**. DO NOT post duplicates
- [X] I've read the [guidelines for opening an issue](https://github.com/yt-dlp/yt-dlp/blob/master/CONTRIBUTING.md#opening-an-issue)
- [ ] I've read about [sharing account credentials](https://github.com/yt-dlp/yt-dlp/blob/master/CONTRIBUTING.md#are-you-willing-to-share-account-details-if-needed) and I'm willing to share it if required
### Region
Any
### Example URLs
https://www.youtube.com/@TaylorSwift/releases
### Provide a description that is worded well enough to be understood
At the moment, using `--download-archive` will record video IDs of already downloaded videos and skip over these videos if they are encountered again. When passing (e.g.) a YouTube releases page to yt-dlp, the following can occur: If multiple releases of an artist contain the same video, it will be skipped every time after the first. This leads to folders that are missing songs with no clear way of copying them over (which is at least problematic for my setup of listening to music locally). Disabling the option circumvents this issue, but the lengthy download times for the full releases page of a productive artist make errors more likely, in which case the entire download would have to begin anew.
A `--playlist-download-archive` option or similar could allow the capture of fully downloaded playlists on completion, keeping the main benefit of `--download-archive` while also not skipping over duplicate videos.
The implementation of this would work very similarly to that of `--download-archive`. `YoutubeDL._playlist_urls` does not do the same job as it's updated before playlist processing and its contents are not stored in any file. I can't judge whether `_playlist_urls` could be updated after playlist processing with no harm to other functionality, or an additional set tracking playlist IDs and saving them to an archive file would be better.
### Provide verbose output that clearly demonstrates the problem
- [X] Run **your** yt-dlp command with **-vU** flag added (`yt-dlp -vU <your command line>`)
- [ ] If using API, add `'verbose': True` to `YoutubeDL` params instead
- [X] Copy the WHOLE output (starting with `[debug] Command-line config`) and insert it below
### Complete Verbose Output
```shell
(don't know what to put here, everything is working as intended)
```
| enhancement,triage | low | Critical |
2,764,944,198 | pytorch | With FSDP2, a small tensor on a 1-GPU world size has grad=0 | ### 🐛 Describe the bug
I train a model normally, and one of the parameters remains at 0 throughout the run. Its grad is always zero, but it should be a large value.
Ablations:
If I use world_size 8, I don't see this. The parameter moves and the grad is 30000 rather than 0.
If I change the parameter from shape (1,) to shape (1, 1), the grad remains 0.
If I change the parameter from shape (1,) to shape (2,) and use `torch.mean(my_param)`, the grad remains 0.
If I change the parameter from shape (1,) to shape (10000000,) and use `torch.mean(my_param)`, the grad is non-zero and the parameter trains normally.
If I change the parameter from shape (1,) to shape (), I am told `ValueError: fully_shard doesn't support salar parameters. Change log_multiplier to a 1D tensor with numel equal to 1.` (This is a known limitation.)
I use 3 other instances of this class. Those instances do not have this problem and their gradient works normally. All the instances which have problems are in FSDP2 submodules, and all the instances without problems are in the root FSDP2 module. I do not know if this is connected. These other instances have numel 256, 768, and 1.
When I check `my_parameter.requires_grad`, it's `True`.
I unfortunately am too busy to produce a repro in the next week. Some brief attempts at creating one from scratch did not produce this error. For example, the following code works fine and does not exhibit the error (it's not a repro):
```
# torchrun --standalone --nnodes=1 --nproc-per-node=1 fsdp2_1nodes.py
import torch
from torch.distributed._tensor import DTensor, Shard, Replicate, distribute_tensor, distribute_module, init_device_mesh
import os
import torch.distributed as dist
import datetime
import torch.nn as nn
import torch.nn.functional as F
from torch.distributed._composable.fsdp import fully_shard, MixedPrecisionPolicy
world_size = int(os.getenv("WORLD_SIZE", None))
local_rank = int(os.getenv("LOCAL_RANK", None))
global_rank = int(os.getenv("RANK", None))
print(f"world_size: {world_size}, local_rank: {local_rank}, global_rank: {global_rank}")
dist.init_process_group(
backend="cpu:gloo,cuda:nccl",
init_method=None,
world_size=world_size,
rank=global_rank,
device_id=torch.device(f"cuda:{local_rank}"),
timeout=datetime.timedelta(seconds=120),
)
torch.cuda.set_device(local_rank)
device_mesh = init_device_mesh("cuda", (1,))
model = torch.nn.Linear(8, 8, device=f"cuda:{local_rank}")
class ExpMultiply(nn.Module):
def __init__(self, shape=(1, 1), starting_value=0.0):
super().__init__()
# any init here would not survive FSDP1/FSDP2 sharding.
# shape must be 1D instead of 0D to make FSDP1 happy. "ValueError: FSDP doesn't support salar parameters. Change resnets.0.resnet_blocks.0.skip_projection_multiplier to a 1D tensor with numel equal to 1."
self.log_multiplier = torch.nn.Parameter(
torch.empty(shape, dtype=torch.float32, device=f"cuda:{local_rank}")
)
self.starting_value = starting_value
def init_weights(self, generator=None):
# torch.nn.init.constant_(self.log_multiplier, self.starting_value)
torch.nn.init.zeros_(self.log_multiplier)
def forward(self, x):
return torch.mul(x, torch.exp(self.log_multiplier + self.starting_value))
a = ExpMultiply((1,), 1.0)
fully_shard(model)
fully_shard(a)
nn.init.zeros_(model.weight)
a.init_weights()
print(model.weight)
a(model(torch.randn(8, 8, device=f"cuda:{local_rank}"))).sum().backward()
print(model.weight.grad)
print(a.log_multiplier.grad)
```
To exhibit the issue, `a.log_multiplier.grad` would have to be 0. It is not.
### Versions
```
Collecting environment information...
PyTorch version: 2.5.1
Is debug build: False
CUDA used to build PyTorch: 12.6
ROCM used to build PyTorch: N/A
OS: Ubuntu 22.04.5 LTS (x86_64)
GCC version: (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0
Clang version: Could not collect
CMake version: version 3.31.1
Libc version: glibc-2.35
Python version: 3.10.12 (main, Nov 6 2024, 20:22:13) [GCC 11.4.0] (64-bit runtime)
Python platform: Linux-6.5.13-650-3434-22042-coreweave-1-x86_64-with-glibc2.35
Is CUDA available: True
CUDA runtime version: 12.6.85
CUDA_MODULE_LOADING set to: LAZY
GPU models and configuration: GPU 0: NVIDIA H100 80GB HBM3
Nvidia driver version: 535.216.01
cuDNN version: Probably one of the following:
/usr/lib/x86_64-linux-gnu/libcudnn.so.9.5.1
/usr/lib/x86_64-linux-gnu/libcudnn_adv.so.9.5.1
/usr/lib/x86_64-linux-gnu/libcudnn_cnn.so.9.5.1
/usr/lib/x86_64-linux-gnu/libcudnn_engines_precompiled.so.9.5.1
/usr/lib/x86_64-linux-gnu/libcudnn_engines_runtime_compiled.so.9.5.1
/usr/lib/x86_64-linux-gnu/libcudnn_graph.so.9.5.1
/usr/lib/x86_64-linux-gnu/libcudnn_heuristic.so.9.5.1
/usr/lib/x86_64-linux-gnu/libcudnn_ops.so.9.5.1
HIP runtime version: N/A
MIOpen runtime version: N/A
Is XNNPACK available: True
CPU:
Architecture: x86_64
CPU op-mode(s): 32-bit, 64-bit
Address sizes: 46 bits physical, 57 bits virtual
Byte Order: Little Endian
CPU(s): 128
On-line CPU(s) list: 0-127
Vendor ID: GenuineIntel
Model name: Intel(R) Xeon(R) Platinum 8462Y+
CPU family: 6
Model: 143
Thread(s) per core: 2
Core(s) per socket: 32
Socket(s): 2
Stepping: 8
CPU max MHz: 4100.0000
CPU min MHz: 800.0000
BogoMIPS: 5600.00
Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf tsc_known_freq pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb cat_l3 cat_l2 cdp_l3 invpcid_single cdp_l2 ssbd mba ibrs ibpb stibp ibrs_enhanced tpr_shadow flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb intel_pt avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local split_lock_detect avx_vnni avx512_bf16 wbnoinvd dtherm ida arat pln pts hfi vnmi avx512vbmi umip pku ospke waitpkg avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg tme avx512_vpopcntdq la57 rdpid bus_lock_detect cldemote movdiri movdir64b enqcmd fsrm md_clear serialize tsxldtrk pconfig arch_lbr ibt amx_bf16 avx512_fp16 amx_tile amx_int8 flush_l1d arch_capabilities
Virtualization: VT-x
L1d cache: 3 MiB (64 instances)
L1i cache: 2 MiB (64 instances)
L2 cache: 128 MiB (64 instances)
L3 cache: 120 MiB (2 instances)
NUMA node(s): 2
NUMA node0 CPU(s): 0,2,4,6,8,10,12,14,16,18,20,22,24,26,28,30,32,34,36,38,40,42,44,46,48,50,52,54,56,58,60,62,64,66,68,70,72,74,76,78,80,82,84,86,88,90,92,94,96,98,100,102,104,106,108,110,112,114,116,118,120,122,124,126
NUMA node1 CPU(s): 1,3,5,7,9,11,13,15,17,19,21,23,25,27,29,31,33,35,37,39,41,43,45,47,49,51,53,55,57,59,61,63,65,67,69,71,73,75,77,79,81,83,85,87,89,91,93,95,97,99,101,103,105,107,109,111,113,115,117,119,121,123,125,127
Vulnerability Gather data sampling: Not affected
Vulnerability Itlb multihit: Not affected
Vulnerability L1tf: Not affected
Vulnerability Mds: Not affected
Vulnerability Meltdown: Not affected
Vulnerability Mmio stale data: Not affected
Vulnerability Retbleed: Not affected
Vulnerability Spec rstack overflow: Not affected
Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl
Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization
Vulnerability Spectre v2: Mitigation; Enhanced / Automatic IBRS; IBPB conditional; RSB filling; PBRSB-eIBRS SW sequence; BHI BHI_DIS_S
Vulnerability Srbds: Not affected
Vulnerability Tsx async abort: Not affected
Versions of relevant libraries:
[pip3] clip-anytorch==2.6.0
[pip3] dctorch==0.1.2
[pip3] DISTS-pytorch==0.1
[pip3] gpytorch==1.13
[pip3] lovely-numpy==0.2.13
[pip3] mypy-extensions==1.0.0
[pip3] numpy==1.24.4
[pip3] torch==2.5.1
[pip3] torchaudio==2.5.0
[pip3] torchdiffeq==0.2.5
[pip3] torchsde==0.2.6
[pip3] torchvision==0.20.0
[pip3] triton==3.1.0
[pip3] welford-torch==0.2.4
[conda] Could not collect
```
cc @H-Huang @awgu @kwen2501 @wanchaol @fegin @fduwjj @wz337 @wconstab @d4l3k @c-p-i-o @zhaojuanmao @mrshenli @rohan-varma @chauhang | oncall: distributed,triaged,module: fsdp | low | Critical |
2,764,963,436 | flutter | [video_player] The video player temporarily hides when the app resumes on Android 11 above. | ### Steps to reproduce
The video player temporarily hides when the app resumes on Android 11 above.
### Expected results
Ensure the video always displays and play when the app resumes.
### Actual results
<details open><summary>Logs</summary>
```console
-> App is backgroud
I/OplusFeedbackInfo(31957): 0xb4000075b3e57400 c2.mtk.avc.decoder 1080x1080 inputFps=28 outputFps=27 renderFps=30, discardFps=0
D/BufferPoolAccessor2.0(31957): bufferpool2 0xb400007545830a28 : 9(18846720 size) total buffers - 9(18846720 size) used buffers - 576/585 (recycle/alloc) - 9/584 (fetch/transfer)
D/VRI[MainActivity](31957): onFocusEvent false
I/flutter (31957): AppLifecycleState --> AppLifecycleState.inactive
D/ViewRootImplExtImpl(31957): onDisplayChanged 0 for VRI android.view.ViewRootImpl@51b0a06
I/OplusFeedbackInfo(31957): 0xb4000075b3e57400 c2.mtk.avc.decoder 1080x1080 inputFps=30 outputFps=30 renderFps=30, discardFps=0
D/VRI[MainActivity](31957): dispatchAppVisibility visible:false
I/SurfaceView(31957): 228513960 surfaceDestroyed
D/BLASTBufferQueue(31957): [SurfaceView[com.example.festo_post/com.example.festo_post.MainActivity]#4](f:0,a:1) destructor()
D/BufferQueueConsumer(31957): [SurfaceView[com.example.festo_post/com.example.festo_post.MainActivity]#4(BLAST Consumer)4](id:7cd500000007,api:0,p:-1,c:31957) disconnect
D/SurfaceView(31957): 196013809positionLost mSurfaceControl is null return;
D/CCodecBufferChannel(31957): [c2.mtk.avc.decoder#751] DEBUG: elapsed: mInputMetEos 17, hasPendingOutputsInClient 0, n=1 [in=4 pipeline=0 out=13]
D/PipelineWatcher(31957): [0xb4000075085da280] elapsed: mFramesInPipeline 9, n 17
D/BLASTBufferQueue(31957): [VRI[MainActivity]#3](f:0,a:1) destructor()
D/BufferQueueConsumer(31957): [VRI[MainActivity]#5(BLAST Consumer)5](id:7cd500000009,api:0,p:-1,c:31957) disconnect
D/VRI[MainActivity](31957): setWindowStopped stopped:true
D/BufferQueueConsumer(31957): [ImageReader-1x1f22m5-31957-2](id:7cd500000008,api:3,p:31957,c:31957) disconnect
I/ExoPlayerImpl(31957): Release 84e25e0 [AndroidXMedia3/1.4.1] [OP555BL1, IV2201, OnePlus, 33] [media3.common, media3.exoplayer, media3.decoder, media3.datasource, media3.extractor]
E/BufferQueueProducer(31957): [ImageReader-1x1f22m5-31957-2](id:7cd500000008,api:3,p:31957,c:31957) queueBuffer: BufferQueue has been abandoned
E/Codec2-OutputBufferQueue(31957): outputBuffer -- queueBuffer() failed on bufferqueue-based block. Error = -19.
I/CCodecBufferChannel(31957): [c2.mtk.avc.decoder#204] queueBuffer failed: -19
E/OplusCCodec(31957): onError [68]: (0xb4000075b7ae3380) err=-2147483648 actionCode=0
E/MediaCodec(31957): rendering to non-initilized(obsolete) surface
E/MediaCodec(31957): Codec reported err 0x80000000/UNKNOWN_ERROR, actionCode 0, while in state 6/STARTED
D/MediaCodec(31957): flushMediametrics
D/MediaCodec(31957): [0xb4000075b7aea000] setState: 0
D/MediaCodec(31957): [0xb4000075b7aea000] [c2.mtk.avc.decoder] disconnectFromSurface: mSurface 0xb4000075b7a61000
-> App is foreground
D/VRI[MainActivity](31957): dispatchAppVisibility visible:true
D/VRI[MainActivity](31957): setWindowStopped stopped:false
I/flutter (31957): AppLifecycleState --> AppLifecycleState.hidden
I/flutter (31957): AppLifecycleState --> AppLifecycleState.inactive
I/ExoPlayerImpl(31957): Init 867f62b [AndroidXMedia3/1.4.1] [OP555BL1, IV2201, OnePlus, 33]
D/BufferQueueConsumer(31957): [](id:7cd50000000b,api:0,p:-1,c:31957) connect: controlledByApp=true
I/Quality (31957): Skipped: false 2 cost 31.380924 refreshRate 11052179 bit true processName com.example.festo_post
D/BufferQueueConsumer(31957): [](id:7cd50000000c,api:0,p:-1,c:31957) connect: controlledByApp=false
E/IPCThreadState(31957): attemptIncStrongHandle(65): Not supported
E/IPCThreadState(31957): attemptIncStrongHandle(61): Not supported
D/TrafficStats(31957): tagSocket(144) with statsTag=0xffffffff, statsUid=-1
D/BufferQueueConsumer(31957): [](id:7cd50000000d,api:0,p:-1,c:31957) connect: controlledByApp=false
I/SurfaceView(31957): 228513960 visibleChanged -- surfaceCreated
E/gralloc4(31957): ERROR: Format allocation info not found for format: 38
E/gralloc4(31957): ERROR: Format allocation info not found for format: 0
E/gralloc4(31957): Invalid base format! req_base_format = 0x0, req_format = 0x38, type = 0x0
E/gralloc4(31957): ERROR: Unrecognized and/or unsupported format 0x38 and usage 0xb00
E/Gralloc4(31957): isSupported(1, 1, 56, 1, ...) failed with 5
E/GraphicBufferAllocator(31957): Failed to allocate (4 x 4) layerCount 1 format 56 usage b00: 5
E/AHardwareBuffer(31957): GraphicBuffer(w=4, h=4, lc=1) failed (Unknown error -5), handle=0x0
E/gralloc4(31957): ERROR: Format allocation info not found for format: 38
E/gralloc4(31957): ERROR: Format allocation info not found for format: 0
E/gralloc4(31957): Invalid base format! req_base_format = 0x0, req_format = 0x38, type = 0x0
E/gralloc4(31957): ERROR: Unrecognized and/or unsupported format 0x38 and usage 0xb00
E/Gralloc4(31957): isSupported(1, 1, 56, 1, ...) failed with 5
E/GraphicBufferAllocator(31957): Failed to allocate (4 x 4) layerCount 1 format 56 usage b00: 5
E/AHardwareBuffer(31957): GraphicBuffer(w=4, h=4, lc=1) failed (Unknown error -5), handle=0x0
I/SurfaceView(31957): 228513960 surfaceChanged -- format=4 w=1080 h=2359
D/VRI[MainActivity](31957): registerCallbacksForSync syncBuffer=false
D/BLASTBufferQueue(31957): [VRI[MainActivity]#7](f:0,a:1) acquireNextBufferLocked size=1080x2400 mFrameNumber=1 applyTransaction=true mTimestamp=64878924207481(auto) mPendingTransactions.size=0 graphicBufferId=137254269879371 transform=0
D/VRI[MainActivity](31957): Received frameCommittedCallback lastAttemptedDrawFrameNum=1 didProduceBuffer=true syncBuffer=false
D/VRI[MainActivity](31957): draw finished.
D/BLASTBufferQueue(31957): [SurfaceView[com.example.festo_post/com.example.festo_post.MainActivity]#8](f:0,a:1) acquireNextBufferLocked size=1080x2359 mFrameNumber=1 applyTransaction=true mTimestamp=64878949113327(auto) mPendingTransactions.size=0 graphicBufferId=137254269879366 transform=0
D/VRI[MainActivity](31957): onFocusEvent true
I/flutter (31957): AppLifecycleState --> AppLifecycleState.resumed
D/ViewRootImplExtImpl(31957): onDisplayChanged 0 for VRI android.view.ViewRootImpl@51b0a06
I/DMCodecAdapterFactory(31957): Creating an asynchronous MediaCodec adapter for track type video
D/TrafficStats(31957): tagSocket(144) with statsTag=0xffffffff, statsUid=-1
D/MediaCodec(31957): CreateByComponentName: name c2.mtk.avc.decoder
```
</details>
### Code sample
<details open><summary>Code sample</summary>
```dart
late VideoPlayerController videoPlayerController;
bool videoInitialized = false;
Container(
child: viewModel.videoInitialized
? AspectRatio(
aspectRatio: viewModel.videoPlayerController.value.aspectRatio,
child: InkWell(
onTap: () => viewModel.videoPlayback(),
child: VideoPlayer(viewModel.videoPlayerController),
),
) : CupertinoActivityIndicator(color: ColorRes.blue1E2A38),
)
void initializeVideo({String? url}) {
videoInitialized = false;
notifyListeners();
videoPlayerController = VideoPlayerController.networkUrl(Uri.parse(url ?? postVideo[selectPostIndex].image ?? ''))
..initialize().then((_) async {
await videoPlayerController.play();
videoPlayerController.setLooping(true);
videoInitialized = true;
notifyListeners();
});
}
Future<void> videoPlayback() async {
if (videoPlayerController.value.isPlaying == false || videoPlayerController.value.isCompleted) {
await videoPlayerController.play();
} else {
await videoPlayerController.pause();
}
notifyListeners();
}
@override
void dispose() {
debugPrint("video disposed...");
WidgetsBinding.instance.removeObserver(this);
videoPlayerController.dispose();
super.dispose();
}
```
</details>
### Screenshots or Video
<details open>
<summary>Screenshots / Video demonstration</summary>
[Upload media here]
Android 11
https://github.com/user-attachments/assets/6b98c197-9473-419a-9eeb-6d2c9ead6a6f
Android 11 above
https://github.com/user-attachments/assets/dd301aa8-031b-4176-a02d-bab1ff2d0d16
</details>
### Logs
<details open><summary>Logs</summary>
```console
[Paste your logs here]
```
</details>
### Flutter Doctor output
<details open><summary>Doctor output</summary>
```console
[√] Flutter (Channel stable, 3.27.1, on Microsoft Windows [Version 10.0.22621.4317], locale en-US)
• Flutter version 3.27.1 on channel stable at D:\flutterSDK
• Upstream repository https://github.com/flutter/flutter.git
• Framework revision 17025dd882 (2 weeks ago), 2024-12-17 03:23:09 +0900
• Engine revision cb4b5fff73
• Dart version 3.6.0
• DevTools version 2.40.2
[√] Windows Version (Installed version of Windows is version 10 or higher)
[√] Android toolchain - develop for Android devices (Android SDK version 35.0.0)
• Android SDK at D:\androidSdk
• Platform android-35, build-tools 35.0.0
• Java binary at: D:\Android Studio\jbr\bin\java
• Java version OpenJDK Runtime Environment (build 21.0.3+-12282718-b509.11)
• All Android licenses accepted.
[√] Chrome - develop for the web
• Chrome at C:\Program Files\Google\Chrome\Application\chrome.exe
[X] Visual Studio - develop Windows apps
X Visual Studio not installed; this is necessary to develop Windows apps.
Download at https://visualstudio.microsoft.com/downloads/.
Please install the "Desktop development with C++" workload, including all of its default components
[√] Android Studio (version 2024.2)
• Android Studio at D:\Android Studio
• Flutter plugin can be installed from:
https://plugins.jetbrains.com/plugin/9212-flutter
• Dart plugin can be installed from:
https://plugins.jetbrains.com/plugin/6351-dart
• android-studio-dir = D:\Android Studio
• Java version OpenJDK Runtime Environment (build 21.0.3+-12282718-b509.11)
[√] Connected device (4 available)
• Mi A3 (mobile) • adb-492fb60d2fec-hqZFnj._adb-tls-connect._tcp • android-arm64 • Android 11 (API 30)
• Windows (desktop) • windows • windows-x64 • Microsoft Windows [Version 10.0.22621.4317]
• Chrome (web) • chrome • web-javascript • Google Chrome 131.0.6778.205
• Edge (web) • edge • web-javascript • Microsoft Edge 131.0.2903.112
[√] Network resources
• All expected network resources are available.
```
</details>
| platform-android,p: video_player,package,e: OS-version specific,P2,team-android,triaged-android | low | Critical |
2,764,976,985 | flutter | [engine] potential crash on deref of canvas_image_ in single_frame_codec.cc. | ### Steps to reproduce
I have a live app using flutter `3.27.1` that i have released yesterday with 30k daily active users.
I have received a new crash that i had not in `3.24.x` apparently from flutter `UI` :
Please see the full [StackTrace](https://github.com/user-attachments/files/18285076/stack.txt) for more information.
### Expected results
The app should not crash
### Actual results
The app is crashing
### Code sample
<details open><summary>Code sample</summary>
```dart
[Paste your code here]
```
</details>
### Screenshots or Video
<details open>
<summary>Screenshots / Video demonstration</summary>
[Upload media here]
</details>
### Logs
<details open><summary>Logs</summary>
```console
Crashed: io.flutter.1.ui
0 Flutter 0x4db148 flutter::SingleFrameCodec::getNextFrame(_Dart_Handle*) + 303 (SkRefCnt.h:303)
1 App 0xd53c stub CallNativeThroughSafepoint + 21820
2 App 0x726c60 _NativeCodec.getNextFrame + 2286 (painting.dart:2286)
3 App 0x726b3c _NativeCodec.getNextFrame + 24 (exceptions.dart:24)
4 App 0x726214 MultiImageStreamCompleter._decodeNextFrameAndSchedule + 133 (multi_image_stream_completer.dart:133)
5 App 0x1b2fb0 ImageStream.addListener + 177 (multi_image_stream_completer.dart:177)
6 App 0x1bbb40 _ImageState._listenToStream + 1233 (image.dart:1233)
7 App 0x1bb300 _ImageState.didChangeDependencies + 1090 (image.dart:1090)
8 App 0xe2d58 StatefulElement.performRebuild + 5794 (framework.dart:5794)
9 App 0x7152a8 BuildScope._tryRebuild + 2697 (framework.dart:2697)
10 App 0x714e98 BuildScope._flushDirtyElements + 2792 (framework.dart:2792)
11 App 0x714d8c BuildOwner.buildScope + 3048 (framework.dart:3048)
12 App 0xded60 _LayoutBuilderElement._rebuildWithConstraints + 194 (layout_builder.dart:194)
13 App 0xdec60 _LayoutBuilderElement._rebuildWithConstraints + 194 (layout_builder.dart:194)
14 App 0x127a98 RenderObject.invokeLayoutCallback.<anonymous closure> + 2738 (object.dart:2738)
15 App 0x71b618 PipelineOwner._enableMutationsToDirtySubtrees + 1108 (object.dart:1108)
16 App 0x71b598 RenderObject.invokeLayoutCallback + 2738 (object.dart:2738)
17 App 0x12a1d8 RenderConstrainedLayoutBuilder.rebuildIfNecessary + 284 (layout_builder.dart:284)
18 App 0x12a08c _RenderLayoutBuilder.performLayout + 379 (layout_builder.dart:379)
19 App 0x757ae4 RenderObject._layoutWithoutResize + 2466 (object.dart:2466)
20 App 0x7579b0 PipelineOwner.flushLayout + 1074 (object.dart:1074)
21 App 0x757a48 PipelineOwner.flushLayout + 1075 (object.dart:1075)
22 App 0x2891fc RendererBinding.drawFrame + 610 (binding.dart:610)
23 App 0x288e70 WidgetsBinding.drawFrame + 1183 (binding.dart:1183)
24 App 0x2887d4 RendererBinding._handlePersistentFrameCallback + 476 (binding.dart:476)
25 App 0x288798 RendererBinding._handlePersistentFrameCallback + 474 (binding.dart:474)
26 App 0x709848 SchedulerBinding._invokeFrameCallback + 1403 (binding.dart:1403)
27 App 0x70960c SchedulerBinding.handleDrawFrame + 144 (growable_array.dart:144)
28 App 0x44c08 SchedulerBinding._handleDrawFrame + 1158 (binding.dart:1158)
29 App 0x44aec SchedulerBinding._handleDrawFrame + 1158 (binding.dart:1158)
30 App 0x3e280 _invoke + 314 (hooks.dart:314)
31 App 0x431ac PlatformDispatcher._drawFrame + 426 (platform_dispatcher.dart:426)
32 App 0x43170 _drawFrame + 281 (hooks.dart:281)
33 App 0x431dc _drawFrame + 281 (hooks.dart:281)
34 App 0xfb8c stub InvokeDartCode + 31628
35 Flutter 0x63c034 dart::DartEntry::InvokeFunction(dart::Function const&, dart::Array const&, dart::Array const&) + 33 (allocation.h:33)
36 Flutter 0x7495bc Dart_InvokeClosure + 4664 (dart_api_impl.cc:4664)
37 Flutter 0x5cb3dc flutter::Shell::OnAnimatorBeginFrame(fml::TimePoint, unsigned long long) + 30 (dart_invoke.cc:30)
38 Flutter 0x5adc78 std::_fl::__function::__func<flutter::Animator::AwaitVSync()::$_0, std::_fl::allocator<flutter::Animator::AwaitVSync()::$_0>, void (std::_fl::unique_ptr<flutter::FrameTimingsRecorder, std::_fl::default_delete<flutter::FrameTimingsRecorder>>)>::operator()(std::_fl::unique_ptr<flutter::FrameTimingsRecorder, std::_fl::default_delete<flutter::FrameTimingsRecorder>>&&) + 186 (ref_ptr.h:186)
39 Flutter 0x5de554 std::_fl::__function::__func<flutter::VsyncWaiter::FireCallback(fml::TimePoint, fml::TimePoint, bool)::$_0, std::_fl::allocator<flutter::VsyncWaiter::FireCallback(fml::TimePoint, fml::TimePoint, bool)::$_0>, void ()>::operator()() + 302 (unique_ptr.h:302)
40 Flutter 0x85c9c fml::MessageLoopImpl::FlushTasks(fml::FlushType) + 128 (message_loop_impl.cc:128)
41 Flutter 0x89314 fml::MessageLoopDarwin::OnTimerFire(__CFRunLoopTimer*, fml::MessageLoopDarwin*) + 86 (message_loop_darwin.mm:86)
42 CoreFoundation 0xb63f8 <redacted> + 32
43 CoreFoundation 0xb609c <redacted> + 1012
44 CoreFoundation 0xb5bf0 <redacted> + 288
45 CoreFoundation 0x540fc <redacted> + 1856
46 CoreFoundation 0x535b8 CFRunLoopRunSpecific + 572
47 Flutter 0x89400 fml::MessageLoopDarwin::Run() + 52 (message_loop_darwin.mm:52)
48 Flutter 0x890e0 std::_fl::__function::__func<fml::Thread::Thread(std::_fl::function<void (fml::Thread::ThreadConfig const&)> const&, fml::Thread::ThreadConfig const&)::$_0, std::_fl::allocator<fml::Thread::Thread(std::_fl::function<void (fml::Thread::ThreadConfig const&)> const&, fml::Thread::ThreadConfig const&)::$_0>, void ()>::operator()() + 94 (message_loop_impl.cc:94)
49 Flutter 0x88df0 fml::ThreadHandle::ThreadHandle(std::_fl::function<void ()>&&)::$_0::__invoke(void*) + 470 (function.h:470)
50 libsystem_pthread.dylib 0x637c _pthread_start + 136
51 libsystem_pthread.dylib 0x1494 thread_start + 8
```
</details>
### Flutter Doctor output
<details open><summary>Doctor output</summary>
```console
[✓] Flutter (Channel stable, 3.27.1, on macOS 15.2 24C101 darwin-x64, locale fr-FR)
• Flutter version 3.27.1 on channel stable at /Users/foxtom/Desktop/flutter
• Upstream repository https://github.com/flutter/flutter.git
• Framework revision 17025dd882 (2 weeks ago), 2024-12-17 03:23:09 +0900
• Engine revision cb4b5fff73
• Dart version 3.6.0
• DevTools version 2.40.2
[✓] Android toolchain - develop for Android devices (Android SDK version 35.0.0)
• Android SDK at /Users/foxtom/Library/Android/sdk
• Platform android-35, build-tools 35.0.0
• Java binary at: /Applications/Android Studio.app/Contents/jbr/Contents/Home/bin/java
• Java version OpenJDK Runtime Environment (build 21.0.3+-79915915-b509.11)
• All Android licenses accepted.
[✓] Xcode - develop for iOS and macOS (Xcode 16.2)
• Xcode at /Applications/Xcode.app/Contents/Developer
• Build 16C5032a
• CocoaPods version 1.16.2
[✓] Chrome - develop for the web
• Chrome at /Applications/Google Chrome.app/Contents/MacOS/Google Chrome
[✓] Android Studio (version 2024.2)
• Android Studio at /Applications/Android Studio.app/Contents
• Flutter plugin can be installed from:
🔨 https://plugins.jetbrains.com/plugin/9212-flutter
• Dart plugin can be installed from:
🔨 https://plugins.jetbrains.com/plugin/6351-dart
• Java version OpenJDK Runtime Environment (build 21.0.3+-79915915-b509.11)
[✓] VS Code (version 1.96.2)
• VS Code at /Applications/Visual Studio Code.app/Contents
• Flutter extension can be installed from:
🔨 https://marketplace.visualstudio.com/items?itemName=Dart-Code.flutter
[✓] Connected device (4 available)
• Now You See Me (mobile) • 00008020-001204401E78002E • ios • iOS 18.2 22C152
• macOS (desktop) • macos • darwin-x64 • macOS 15.2 24C101 darwin-x64
• Chrome (web) • chrome • web-javascript • Google Chrome 131.0.6778.205
[✓] Network resources
• All expected network resources are available.
• No issues found!
```
</details>
| c: regression,c: crash,platform-ios,engine,a: images,a: production,P2,needs repro info,team-engine,triaged-engine | low | Critical |
2,764,991,659 | godot | TileMap node editor gets confused when mixing two actions | ### Tested versions
v4.4.dev7.official [46c8f8c5c]
v3.6.stable.official [de2f0f147]
### System information
win11
### Issue description
The issue is that the editor gets confused when you mix these two actions:
Copy an area of the TileMap node and while keeping the area copied, scroll in the editor by pressing the spacebar.
### Steps to reproduce
In Godot 4, the area is not selected by pressing the M key, but by activating the selection tool (the arrow icon next to the pencil) in the TileMap node.
In Godot 4, but you need to use CTRL + V immediately after copying the area with CTRL + C.
This is described for Godot 3.6:
1. In the TileMap node:
2. Press the M key to select an area.
3. Press CTRL + C to copy it.
4. At this point, the area is copied. Now, hold down the spacebar and press the left mouse button to move the scroll in the editor.
5. Release the spacebar and mouse button, and you’ll notice the editor gets stuck scrolling. Now, if you move the mouse, the editor will scroll automatically without you giving any further commands.
### Minimal reproduction project (MRP)
... | bug,topic:editor,topic:2d | low | Minor |
2,765,012,389 | godot | Exported property doesn't change when changed in the editor | ### Tested versions
-Reproducible in v4.3.stable.flathub [77dcf97d8] and v4.2.2.stable.official [15073afe3]
### System information
Godot v4.3.stable (77dcf97d8) - Freedesktop SDK 24.08 (Flatpak runtime) - X11 - Vulkan (Forward+) - dedicated AMD Radeon RX 6600 (RADV NAVI23) - 12th Gen Intel(R) Core(TM) i5-12600K (16 Threads)
### Issue description
When a GDScript exports a property, if it's of type Node (or Node2D/3D) it'll not change when reassigned through the editor. They can however be modified through script.
As explained in the [docs](https://docs.godotengine.org/en/4.3/tutorials/scripting/gdscript/gdscript_exports.html#doc-gdscript-exports), exported properties can be changed in the editor while running a scene. But for the case of Nodes this is not the case. They are set once when the scene starts running and can't be changed form the UI editor.
### Steps to reproduce
1. Export a node property in any `GDScript`.
2. Make `_process` spam print the exported property.
3. Run the scene.
4. Switch the exported property in the editor.
5. The property doesn't change.
### Minimal reproduction project (MRP)
[export_bug.zip](https://github.com/user-attachments/files/18285240/export_bug.zip)
| bug,topic:editor,usability | low | Critical |
2,765,053,868 | ollama | Reverse download Progress During Model Pull Ollama pull phi3:medium | ### What is the issue?
While attempting to pull a model using Ollama, I am facing the inconsistent increase decrease in the progress while pull the model from ollama using command e.g ollama pull phi3:medium. what can be the reason behind this.
Note: having a stable internet connection.
### OS
Windows
### GPU
Nvidia
### CPU
_No response_
### Ollama version
0.5.4 | bug | low | Minor |
2,765,081,558 | vscode | Editor Context Menu Item Order | <!-- ⚠️⚠️ Do Not Delete This! feature_request_template ⚠️⚠️ -->
<!-- Please read our Rules of Conduct: https://opensource.microsoft.com/codeofconduct/ -->
<!-- Please search existing issues to avoid creating duplicates. -->
<!-- Describe the feature you'd like. -->
Allow the order of items in the editor context menu to be configurable. Or, place extension context menu items after the default items.
Would make developer experience more efficient (eliminate a mouse scroll) .
Would be useful in situations where extension shortcuts conflict with VSCode's, (ex Vim). This would allow native shortcuts to be preserved.
| feature-request,menus | low | Minor |
2,765,082,331 | deno | [deno install] Could not find Sharp. Please install Sharp (`sharp`) | Version: Deno 2.1.4
The repo I have is this small astro site:
https://github.com/maplibre/maplibre.github.io
If i `npm i` and then `deno task build`, then everything works.
If i `deno i --allow-scripts` and then `deno task build`, then I see:
```sh
generating optimized images
[CouldNotTransformImage] Could not transform image `/_astro/maplibre-logo.wyLiUNdu.svg`. See the stack trace for more information.
Hint:
This is often caused by a corrupted or malformed image. Re-exporting the image from your image editor may fix this issue.
Error reference:
https://docs.astro.build/en/reference/errors/could-not-transform-image/
Location:
/Users/admin/repos/maplibre.github.io/node_modules/.deno/[email protected]/node_modules/astro/dist/assets/build/generate.js:158:21
Stack trace:
at generateImageInternal (/Users/admin/repos/maplibre.github.io/node_modules/.deno/[email protected]/node_modules/astro/dist/assets/build/generate.js:158:21)
at async /Users/admin/repos/maplibre.github.io/node_modules/.deno/[email protected]/node_modules/p-queue/dist/index.js:187:36
Caused by:
Could not find Sharp. Please install Sharp (`sharp`) manually into your project or migrate to another image service.
at loadSharp (/Users/admin/repos/maplibre.github.io/dist/chunks/sharp_BtaBROoe.mjs:16:11)
at async generateImageInternal (/Users/admin/repos/maplibre.github.io/node_modules/.deno/[email protected]/node_modules/astro/dist/assets/build/generate.js:152:26)
at async /Users/admin/repos/maplibre.github.io/node_modules/.deno/[email protected]/node_modules/p-queue/dist/index.js:187:36
``` | working as designed,install | low | Critical |
2,765,115,683 | rust | Higher ranked lifetime error when checking auto traits of async functions containing calls to async closures which capture a local | I tried this code:
```rust
#![feature(async_fn_traits)]
use std::ops::AsyncFn;
// this function is important, inlining it breaks the poc.
// We also tried replacing it with `identity` but the fact that this is an
// async function calling the closure inside is also relevant.
async fn do_not_inline(f: impl AsyncFn()) {
f().await;
}
fn foo() -> impl Send {
async move {
// just replacing this with unit, leaves the error with `Send` but fixes the
// "higher-ranked lifetime error"
let s = &();
do_not_inline(async || {
&s;
})
.await;
}
}
```
I expected to see this happen: compilation succeeds
Instead, this happened:
```
error: implementation of `Send` is not general enough
--> src/lib.rs:13:5
|
13 | / async move {
14 | | // just replacing this with unit, leaves the error with `Send` but fixes the
15 | | // "higher-ranked lifetime error"
16 | | let s = &();
... |
21 | | .await;
22 | | }
| |_____^ implementation of `Send` is not general enough
|
= note: `Send` would have to be implemented for the type `&'0 &()`, for any lifetime `'0`...
= note: ...but `Send` is actually implemented for the type `&'1 &()`, for some specific lifetime `'1`
error: higher-ranked lifetime error
--> src/lib.rs:13:5
|
13 | / async move {
14 | | // just replacing this with unit, leaves the error with `Send` but fixes the
15 | | // "higher-ranked lifetime error"
16 | | let s = &();
... |
21 | | .await;
22 | | }
| |_____^
error: could not compile `noteslsp` (lib) due to 2 previous errors
```
try it here: https://play.rust-lang.org/?version=nightly&mode=debug&edition=2021&gist=ab71ed9cfa6f91320c7a24fe7f2bdca9
note, we got here through a bigger example, the `impl Send` used to come from the `async_trait` library where it produced `Pin<Box<dyn Future<Output=()> + Send>>` but most of that was not relevant for the mcve.
### Meta
`rustc --version --verbose`:
```
rustc 1.85.0-nightly (d117b7f21 2024-12-31)
binary: rustc
commit-hash: d117b7f211835282b3b177dc64245fff0327c04c
commit-date: 2024-12-31
host: x86_64-unknown-linux-gnu
release: 1.85.0-nightly
LLVM version: 19.1.6
```
cc: @compiler-errors
@rustbot label +F-async_closure +T-compiler +A-auto-traits | T-compiler,C-bug,F-async_closure,A-auto-traits | low | Critical |
2,765,123,161 | react-native | Warning: Error: Exception in HostFunction: Loss of precision during arithmetic conversion: (long) 0.01 | ### Description
(NOBRIDGE) ERROR Warning: Error: Exception in HostFunction: Loss of precision during arithmetic conversion: (long) 0.01
This error is located at:
in RNSScreen (created by Animated(Anonymous))
in Animated(Anonymous)
in Suspender (created by Freeze)
in Suspense (created by Freeze)
in Freeze (created by DelayedFreeze)
in DelayedFreeze
in InnerScreen (created by Screen)
in Screen (created by SceneView)
in SceneView (created by NativeStackViewInner)
in RNSScreenStack (created by ScreenStack)
in Unknown (created by ScreenStack)
in ScreenStack (created by NativeStackViewInner)
in NativeStackViewInner (created by NativeStackView)
in RCTView (created by View)
in View (created by SafeAreaProviderCompat)
in SafeAreaProviderCompat (created by NativeStackView)
in NativeStackView (created by NativeStackNavigator)
in PreventRemoveProvider (created by NavigationContent)
in NavigationContent
in Unknown (created by NativeStackNavigator)
in NativeStackNavigator (created by ApplicationNavigator)
in EnsureSingleNavigator
in BaseNavigationContainer
in ThemeProvider
in NavigationContainerInner (created by ApplicationNavigator)
in RNCSafeAreaProvider (created by SafeAreaProvider)
in SafeAreaProvider (created by ApplicationNavigator)
in ApplicationNavigator (created by Root)
in ThemeProvider (created by Root)
in ThemeProvider (created by PaperProvider)
in RCTView (created by View)
in View (created by Portal.Host)
in Portal.Host (created by PaperProvider)
in RNCSafeAreaProvider (created by SafeAreaProvider)
in SafeAreaProvider (created by SafeAreaInsetsContext)
in SafeAreaProviderCompat (created by PaperProvider)
in PaperProvider (created by Root)
in RNGestureHandlerRootView (created by GestureHandlerRootView)
in GestureHandlerRootView (created by Root)
in Root
in RCTView (created by View)
in View (created by AppContainer)
in RCTView (created by View)
in View (created by AppContainer)
in AppContainer
in nkcc_mobile_app(RootComponent)
### Steps to reproduce
1. Install react native 0.76.5
install these dependencies
"@react-native-masked-view/masked-view": "^0.3.2",
"@react-navigation/bottom-tabs": "^6.6.1",
"@react-navigation/native": "^6.1.18",
"@react-navigation/native-stack": "^6.11.0",
"@react-navigation/stack": "^6.4.1",
"i18next": "^24.2.0",
"intl-pluralrules": "^2.0.1",
"ky": "^1.7.4",
"lottie-react-native": "^7.1.0",
"react": "18.3.1",
"react-error-boundary": "^5.0.0",
"react-i18next": "^15.4.0",
"react-native": "0.76.5",
"react-native-bootsplash": "^6.3.2",
"react-native-gesture-handler": "^2.21.2",
"react-native-linear-gradient": "^2.8.3",
"react-native-mmkv": "^3.2.0",
"react-native-paper": "^5.12.5",
"react-native-reanimated": "^3.16.6",
"react-native-safe-area-context": "^5.0.0",
"react-native-screens": "4.4.0",
"react-native-svg": "^15.10.1",
"react-native-video": "^6.8.2",
"react-native-vision-camera": "^4.6.3",
"zod": "^3.24.1"
Try running on android.
### React Native Version
0.76.5
### Affected Platforms
Runtime - Android
### Output of `npx react-native info`
```text
npx react-native info
(node:27112) [DEP0040] DeprecationWarning: The `punycode` module is deprecated. Please use a userland alternative instead.
(Use `node --trace-deprecation ...` to show where the warning was created)
info Fetching system and libraries information...
System:
OS: macOS 15.0
CPU: (10) arm64 Apple M4
Memory: 101.94 MB / 16.00 GB
Shell:
version: "5.9"
path: /bin/zsh
Binaries:
Node:
version: 22.12.0
path: ~/.nvm/versions/node/v22.12.0/bin/node
Yarn:
version: 4.6.0
path: ~/.nvm/versions/node/v22.12.0/bin/yarn
npm:
version: 10.9.2
path: ~/.nvm/versions/node/v22.12.0/bin/npm
Watchman:
version: 2024.12.02.00
path: /opt/homebrew/bin/watchman
Managers:
CocoaPods:
version: 1.14.3
path: /Users/nitesh/.rvm/rubies/ruby-2.7.4/bin/pod
SDKs:
iOS SDK:
Platforms:
- DriverKit 24.2
- iOS 18.2
- macOS 15.2
- tvOS 18.2
- visionOS 2.2
- watchOS 11.2
Android SDK:
API Levels:
- "31"
- "33"
- "34"
- "35"
Build Tools:
- 33.0.1
- 34.0.0
- 35.0.0
- 36.0.0
System Images:
- android-35 | Google Play ARM 64 v8a
Android NDK: Not Found
IDEs:
Android Studio: 2024.2 AI-242.23339.11.2421.12700392
Xcode:
version: 16.2/16C5032a
path: /usr/bin/xcodebuild
Languages:
Java:
version: 17.0.13
path: /opt/homebrew/opt/openjdk@17/bin/javac
Ruby:
version: 2.7.4
path: /Users/nitesh/.rvm/rubies/ruby-2.7.4/bin/ruby
npmPackages:
"@react-native-community/cli":
installed: 15.1.3
wanted: 15.1.3
react:
installed: 18.3.1
wanted: 18.3.1
react-native:
installed: 0.76.5
wanted: 0.76.5
react-native-macos: Not Found
npmGlobalPackages:
"*react-native*": Not Found
Android:
hermesEnabled: true
newArchEnabled: true
iOS:
hermesEnabled: true
newArchEnabled: true
```
### Stacktrace or Logs
```text
Warning: Error: Exception in HostFunction: Loss of precision during arithmetic conversion: (long) 0.01
This error is located at:
in RNSScreen (created by Animated(Anonymous))
in Animated(Anonymous)
in Suspender (created by Freeze)
in Suspense (created by Freeze)
in Freeze (created by DelayedFreeze)
in DelayedFreeze
in InnerScreen (created by Screen)
in Screen (created by SceneView)
in SceneView (created by NativeStackViewInner)
in RNSScreenStack (created by ScreenStack)
in Unknown (created by ScreenStack)
in ScreenStack (created by NativeStackViewInner)
in NativeStackViewInner (created by NativeStackView)
in RCTView (created by View)
in View (created by SafeAreaProviderCompat)
in SafeAreaProviderCompat (created by NativeStackView)
in NativeStackView (created by NativeStackNavigator)
in PreventRemoveProvider (created by NavigationContent)
in NavigationContent
in Unknown (created by NativeStackNavigator)
in NativeStackNavigator (created by ApplicationNavigator)
in EnsureSingleNavigator
in BaseNavigationContainer
in ThemeProvider
in NavigationContainerInner (created by ApplicationNavigator)
in RNCSafeAreaProvider (created by SafeAreaProvider)
in SafeAreaProvider (created by ApplicationNavigator)
in ApplicationNavigator (created by Root)
in ThemeProvider (created by Root)
in ThemeProvider (created by PaperProvider)
in RCTView (created by View)
in View (created by Portal.Host)
in Portal.Host (created by PaperProvider)
in RNCSafeAreaProvider (created by SafeAreaProvider)
in SafeAreaProvider (created by SafeAreaInsetsContext)
in SafeAreaProviderCompat (created by PaperProvider)
in PaperProvider (created by Root)
in RNGestureHandlerRootView (created by GestureHandlerRootView)
in GestureHandlerRootView (created by Root)
in Root
in RCTView (created by View)
in View (created by AppContainer)
in RCTView (created by View)
in View (created by AppContainer)
in AppContainer
in nkcc_mobile_app(RootComponent)
```
### Reproducer
https://github.com/neeteshraj/nkcc/tree/feat/home-screen
### Screenshots and Videos
<img width="1512" alt="Screenshot 2025-01-01 at 21 01 31" src="https://github.com/user-attachments/assets/a1c615d6-cd90-4a2b-972b-7c24e87efad5" />
| Issue: Author Provided Repro | low | Critical |
2,765,129,917 | rust | `--emit obj` with `--crate-type staticlib` doesn't work when `-C lto=thin` is set | I tried this code:
```rust
// answer.rs
pub fn answer() -> u64 {
42
}
```
And compiled it with:
```
rustc answer.rs --crate-type staticlib --emit obj -C lto=thin
```
I expected to see an object file created. Instead it appears to succeed but no object file is produced.
### Meta
`rustc --version --verbose`:
```
rustc 1.82.0 (f6e511eec 2024-10-15)
binary: rustc
commit-hash: f6e511eec7342f59a25f7c0534f1dbea00d01b14
commit-date: 2024-10-15
host: x86_64-pc-windows-msvc
release: 1.82.0
LLVM version: 19.1.1
``` | T-compiler,C-bug,A-LTO,A-CLI | low | Minor |
2,765,130,216 | kubernetes | ContainerLogManager to rotate logs of all containers in case of disk pressure on host | ### What would you like to be added?
The [ContainerLogManager](https://github.com/kubernetes/kubernetes/blob/master/pkg/kubelet/logs/container_log_manager.go#L52-L60), responsible for log rotation and cleanup of log files of containers should also rotate logs of all containers in case of disk pressure on host.
### Why is this needed?
It often happens that the containers generating heavy log data have compressed log file with size exceeding the containerLogMaxSize limit set in kubelet config.
For example, kubelet has
```
containerLogMaxSize = 200M
containerLogMaxFiles = 6
```
### Spec 1
Continuously generating 10Mib with 0.1 sec sleep in between
```
apiVersion: batch/v1
kind: Job
metadata:
name: generate-huge-logs
spec:
template:
spec:
containers:
- name: log-generator
image: busybox
command: ["/bin/sh", "-c"]
args:
- |
# Generate huge log entries to stdout
start_time=$(date +%s)
log_size=0
target_size=$((4 * 1024 * 1024 * 1024)) # 4 GB target size in bytes
while [ $log_size -lt $target_size ]; do
# Generate 1 MB of random data and write it to stdout
echo "Generating huge log entry at $(date) - $(dd if=/dev/urandom bs=10M count=1 2>/dev/null)"
log_size=$(($log_size + 1048576)) # Increment size by 1MB
sleep 0.1 # Sleep to control log generation speed
done
end_time=$(date +%s)
echo "Log generation completed in $((end_time - start_time)) seconds"
restartPolicy: Never
backoffLimit: 4
```
File sizes
```
-rw-r----- 1 root root 24142862 Jan 1 11:41 0.log
-rw-r--r-- 1 root root 183335398 Jan 1 11:40 0.log.20250101-113948.gz
-rw-r--r-- 1 root root 364144934 Jan 1 11:40 0.log.20250101-114003.gz
-rw-r--r-- 1 root root 487803789 Jan 1 11:40 0.log.20250101-114023.gz
-rw-r--r-- 1 root root 577188544 Jan 1 11:41 0.log.20250101-114047.gz
-rw-r----- 1 root root 730449620 Jan 1 11:41 0.log.20250101-114115
```
### Spec 2
Continuously generating 10Mib with 10 sec sleep in between
```
apiVersion: batch/v1
kind: Job
metadata:
name: generate-huge-logs
spec:
template:
spec:
containers:
- name: log-generator
image: busybox
command: ["/bin/sh", "-c"]
args:
- |
# Generate huge log entries to stdout
start_time=$(date +%s)
log_size=0
target_size=$((4 * 1024 * 1024 * 1024)) # 4 GB target size in bytes
while [ $log_size -lt $target_size ]; do
# Generate 1 MB of random data and write it to stdout
echo "Generating huge log entry at $(date) - $(dd if=/dev/urandom bs=10M count=1 2>/dev/null)"
log_size=$(($log_size + 1048576)) # Increment size by 1MB
sleep 0.1 # Sleep to control log generation speed
done
end_time=$(date +%s)
echo "Log generation completed in $((end_time - start_time)) seconds"
restartPolicy: Never
backoffLimit: 4
```
File sizes
```
-rw-r----- 1 root root 181176268 Jan 1 11:31 0.log
-rw-r--r-- 1 root root 183336647 Jan 1 11:20 0.log.20250101-111730.gz
-rw-r--r-- 1 root root 183323382 Jan 1 11:23 0.log.20250101-112026.gz
-rw-r--r-- 1 root root 183327676 Jan 1 11:26 0.log.20250101-112321.gz
-rw-r--r-- 1 root root 183336376 Jan 1 11:29 0.log.20250101-112616.gz
-rw-r----- 1 root root 205360966 Jan 1 11:29 0.log.20250101-112911
```
If the pod had been generating logs in Gigabytes with minimal delay, it can cause disk pressure on host. | sig/node,kind/feature,needs-triage | low | Major |
2,765,136,117 | neovim | Diff tests are flaky | ### Problem
The `diff mode overlapped diff blocks will be merged` merged tests frequently fail
### Steps to reproduce
run `TEST_FILE=test/functional/ui/diff_spec.lua make test`, possibly several times in row until it fails
Observe that the tests frequently fail, but not exactly on the same line each time. For me it failed 7 times out of 10.
The failures look like this
```
FAILED test/functional/ui/diff_spec.lua @ 1525: diff mode overlapped diff blocks will be merged
test/functional/ui/diff_spec.lua:1658: Row 1 did not match.
Expected:
|*{7: }{27:a}{4: }│{7: }{27:a}{4: }│{7: }{27:^y}{4: }|
|{7: }{27:b}{4: }│{7: }{27:x}{4: }│{7: }{27:y}{4: }|
|{7: }{27:c}{4: }│{7: }{27:c}{4: }│{7: }{27:y}{4: }|
|{1:~ }│{1:~ }│{1:~ }|
|{1:~ }│{1:~ }│{1:~ }|
|{1:~ }│{1:~ }│{1:~ }|
|{1:~ }│{1:~ }│{1:~ }|
|{1:~ }│{1:~ }│{1:~ }|
|{1:~ }│{1:~ }│{1:~ }|
|{1:~ }│{1:~ }│{1:~ }|
|{1:~ }│{1:~ }│{1:~ }|
|{1:~ }│{1:~ }│{1:~ }|
|{1:~ }│{1:~ }│{1:~ }|
|{1:~ }│{1:~ }│{1:~ }|
|{1:~ }│{1:~ }│{1:~ }|
|{1:~ }│{1:~ }│{1:~ }|
|{1:~ }│{1:~ }│{1:~ }|
|{1:~ }│{1:~ }│{1:~ }|
|{2:Xdifile1 Xdifile2 }{3:Xdifile3 }|
| |
Actual:
|*{7: }a │{7: }a │{7: }^a |
|{7: }{27:b}{4: }│{7: }{27:x}{4: }│{7: }{27:y}{4: }|
|{7: }{27:c}{4: }│{7: }{27:c}{4: }│{7: }{27:y}{4: }|
|{1:~ }│{1:~ }│{1:~ }|
|{1:~ }│{1:~ }│{1:~ }|
|{1:~ }│{1:~ }│{1:~ }|
|{1:~ }│{1:~ }│{1:~ }|
|{1:~ }│{1:~ }│{1:~ }|
|{1:~ }│{1:~ }│{1:~ }|
|{1:~ }│{1:~ }│{1:~ }|
|{1:~ }│{1:~ }│{1:~ }|
|{1:~ }│{1:~ }│{1:~ }|
|{1:~ }│{1:~ }│{1:~ }|
|{1:~ }│{1:~ }│{1:~ }|
|{1:~ }│{1:~ }│{1:~ }|
|{1:~ }│{1:~ }│{1:~ }|
|{1:~ }│{1:~ }│{1:~ }|
|{1:~ }│{1:~ }│{1:~ }|
|{2:Xdifile1 Xdifile2 }{3:Xdifile3 }|
| |
```
### Expected behavior
The tests should not fail
### Nvim version (nvim -v)
NVIM v0.11.0-dev-1451+g9d114b7205
### Vim (not Nvim) behaves the same?
N/A
### Operating system/version
Arch Linux
### Terminal name/version
alacritty
### $TERM environment variable
alacritty
### Installation
Build from repo | bug,test | low | Critical |
2,765,146,034 | react | [DevTools Bug] Cannot remove node "92" because no matching node was found in the Store. | ### Website or app
http://localhost:3000/
### Repro steps
I was trying to inspect my component tree via react dev tools, but each time I make an interaction on the website which changes the state, it throws an error
### How often does this bug happen?
Every time
### DevTools package (automated)
react-devtools-extensions
### DevTools version (automated)
6.0.1-c7c68ef842
### Error message (automated)
Cannot remove node "92" because no matching node was found in the Store.
### Error call stack (automated)
```text
at chrome-extension://gpphkfbcpidddadnkolkpfckpihlkkil/build/main.js:1:1173889
at v.emit (chrome-extension://gpphkfbcpidddadnkolkpfckpihlkkil/build/main.js:1:1140783)
at chrome-extension://gpphkfbcpidddadnkolkpfckpihlkkil/build/main.js:1:1142390
at bridgeListener (chrome-extension://gpphkfbcpidddadnkolkpfckpihlkkil/build/main.js:1:1552662)
```
### Error component stack (automated)
_No response_
### GitHub query string (automated)
```text
https://api.github.com/search/issues?q=Cannot remove node because no matching node was found in the Store. in:title is:issue is:open is:public label:"Component: Developer Tools" repo:facebook/react
```
| Type: Bug,Status: Unconfirmed,Component: Developer Tools | low | Critical |
2,765,168,502 | ollama | Runing ollama on Intel Ultra NPU or GPU | After I installed ollama through ollamaSetup, I found that it cannot use my gpu or npu. How to solve this problem?
CPU: intel ultra7 258v
System: windows 11 24h2 | intel,gpu | low | Major |
2,765,170,432 | ollama | DeepSeek VL v2 | https://huggingface.co/collections/deepseek-ai/deepseek-vl2-675c22accc456d3beb4613ab
there are 3 versions: tiny, small and the default | model request | low | Minor |
2,765,171,879 | react-native | Flatlist onMomentumScrollEnd called inconsistently between Android and iOS | ### Description
it seems the behavior isn't consistent between android and ios.
on android it works when you flick and release, it also works when you scroll and hold thereby controlling the scrolling.
on IOS it only works when you flick and let the scroll momentum end by itself.
https://reactnative.dev/docs/scrollview#onmomentumscrollend
`Called when the momentum scroll ends (scroll which occurs as the ScrollView glides to a stop).`
in this case, i believe it means the behavior is incorrect on Android because it's called when it glides to a stop and when the user controls the stop.
or since there's no specific event for when both the scroll and glide are ended by the user controlling it, we should fix the behavior on iOS to behave the same on Android and update the docs to `Called when the momentum scroll ends (scroll which occurs as the ScrollView stops).`
### Steps to reproduce
1. android: flick and release -> momentum end **event called**
2. android: scroll and hold then release -> momentum end **event called**
3. ios: flick and release -> momentum end **event called**
4. ios: scroll and hold then release -> momentum end **event is not called**
### React Native Version
0.76.5
Same behavior on both the **new and old architecture**
### Affected Platforms
Runtime - Android, Runtime - iOS
### Output of `npx react-native info`
```text
expo-env-info 1.2.1 environment info:
System:
OS: macOS 14.3.1
Shell: 5.9 - /bin/zsh
Binaries:
Node: 20.18.0 - ~/.nvm/versions/node/v20.18.0/bin/node
Yarn: 1.22.22 - ~/.nvm/versions/node/v20.18.0/bin/yarn
npm: 10.8.2 - ~/.nvm/versions/node/v20.18.0/bin/npm
Managers:
CocoaPods: 1.16.2 - /opt/homebrew/bin/pod
SDKs:
iOS SDK:
Platforms: DriverKit 23.2, iOS 17.2, macOS 14.2, tvOS 17.2, visionOS 1.0, watchOS 10.2
IDEs:
Android Studio: 2022.3 AI-223.8836.35.2231.11090377
Xcode: 15.2/15C500b - /usr/bin/xcodebuild
npmPackages:
expo: ~52.0.23 => 52.0.23
expo-router: ~4.0.15 => 4.0.15
react: 18.3.1 => 18.3.1
react-dom: 18.3.1 => 18.3.1
react-native: 0.76.5 => 0.76.5
react-native-web: ~0.19.13 => 0.19.13
npmGlobalPackages:
eas-cli: 13.4.2
Expo Workflow: managed
```
### Stacktrace or Logs
```text
no errors, just inconsistent behavior
```
### Reproducer
https://snack.expo.dev/@hichem_fantar/onmomentumscrollend-example
### Screenshots and Videos
Android:
https://github.com/user-attachments/assets/706f34b0-c19c-49c2-887c-d035d2119fee
iOS:
https://github.com/user-attachments/assets/9a0cafe0-7370-4359-bd63-4dcc16cb9a51
| Platform: iOS,Platform: Android,Needs: Triage :mag: | low | Critical |
2,765,189,966 | terminal | Please report XTVERSION in response to CSI > 0 q or set TERM to something other than xterm (or both) | ### Description of the new feature
Ideally I think Windows Terminal would set the environment variable `TERM` to a unique value and also update the existing terminfo databases. However, I understand that the intermediate state that creates where many programs don't recognize the new terminal type is undesirable.
So in the meantime, can Windows Terminal report XTVERSION? From [ctlseqs](https://invisible-island.net/xterm/ctlseqs/ctlseqs.html):
```
CSI > Ps q
Ps = 0 ⇒ Report xterm name and version (XTVERSION).
The response is a DSR sequence identifying the version:
DCS > | text ST
```
This escape sequence is pretty widely supported to send a unique string that identifies the name and version of a terminal. Off the top of my head, VTE-based terminals (such as GNOME Terminal), Konsole, iTerm2, WezTerm, Contour, and kitty all support this escape sequence.
Context: I am currently drafting up a patch to Emacs that will rely either `TERM` or XTVERSION to determine if xterm-mouse-mode is safe to be enabled by default. Emacs wants to see support fo OSC52 copy, bracketed paste, DECSET1000, and DECSET1003 at a minimum and checking XTVERSION or `TERM` is the only way I have to identify if these escape sequences are supported. Also see [Emacs discussion thread](https://debbugs.gnu.org/cgi/bugreport.cgi?bug=74833).
### Proposed technical implementation details
_No response_ | Issue-Feature,Needs-Triage,Needs-Tag-Fix | low | Critical |
2,765,199,435 | godot | Cannot declare virtual method with enum from own class | ### Tested versions
v4.4.dev7
v4.3.stable
v4.2.2.stable
v4.1.stable
### System information
Windows 11 24H2
### Issue description
Attempting to setup a class which defines a virtual method for an enum setup in that class. That is, before `VARIANT_ENUM_CAST` gets setup. Because the logic in the virtual method is declared immediately, any generic calls are established before this crucial step. In this case, it's `PtrToArg` that's setup too early.
### Steps to reproduce
Script excerpt:
```cpp
class Logger : public RefCounted {
GDCLASS(Logger, RefCounted);
protected:
static void _bind_methods();
public:
enum class LogLevel {
DEBUG,
INFO,
WARN,
ERROR,
FATAL,
MAX,
};
virtual void log(const String &p_content, LogLevel p_level, const TypedDictionary<String, Variant> &p_context = {}) = 0;
#define _COMMA ,
GDVIRTUAL3(_log, String, LogLevel, TypedDictionary<String _COMMA Variant>);
#undef _COMMA
};
VARIANT_ENUM_CAST(Logger::LogLevel);
```
Error output:
```
Use of undeclared identifier 'argval2'; did you mean 'argval1'? clang(undeclared_var_use_suggest)
Expected ';' after expression clang(expected_semi_after_expr)
No member named 'EncodeT' in 'PtrToArg<Logger::LogLevel>' clang(no_member)
Use of undeclared identifier 'argval2' clang(undeclared_var_use)
Implicit instantiation of undefined template 'GetTypeInfo<Logger::LogLevel>' clang(template_instantiate_undefined)
type_info.h(62, 8): Template is declared here
```
### Minimal reproduction project (MRP)
N/A | bug,topic:core,usability | low | Critical |
2,765,235,593 | pytorch | cuDNN version is not detected correctly in PyTorch | ### 🐛 Describe the bug
I am experiencing issues with PyTorch not detecting the correct version of cuDNN. Here’s the setup:
I installed Nightly PyTorch 2.6 using the following command:
```python
pip3 install --pre torch --index-url https://download.pytorch.org/whl/nightly/cu118
```
I installed also the latest supported version of cuDNN for CUDA 11.8, which is cuDNN 9.6. see: https://docs.nvidia.com/deeplearning/cudnn/latest/reference/support-matrix.html
When running the following code to check the cuDNN version:
```python
import torch
print(f"CUDNN version: {torch.backends.cudnn.version()}")
```
the returned version is 90100 (cuDNN 9.1), but it should be 90600 (cuDNN 9.6).
### Versions
PyTorch version: 2.6.0.dev20241231+cu118
Is debug build: False
CUDA used to build PyTorch: 11.8
ROCM used to build PyTorch: N/A
OS: Microsoft Windows 11 Home (10.0.22631 64 bits)
GCC version: Could not collect
Clang version: Could not collect
CMake version: Could not collect
Libc version: N/A
Python version: 3.12.8 | packaged by conda-forge | (main, Dec 5 2024, 14:06:27) [MSC v.1942 64 bit (AMD64)] (64-bit runtime)
Python platform: Windows-11-10.0.22631-SP0
Is CUDA available: True
CUDA runtime version: 11.8.89
CUDA_MODULE_LOADING set to: LAZY
GPU models and configuration: GPU 0: NVIDIA GeForce GTX 1650 Ti
Nvidia driver version: 566.36
cuDNN version: C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.8\bin\cudnn_ops64_9.dll
HIP runtime version: N/A
MIOpen runtime version: N/A
Is XNNPACK available: True
CPU:
Name: AMD Ryzen 7 4800H with Radeon Graphics
Manufacturer: AuthenticAMD
Family: 107
Architecture: 9
ProcessorType: 3
DeviceID: CPU0
CurrentClockSpeed: 2900
MaxClockSpeed: 2900
L2CacheSize: 4096
L2CacheSpeed: None
Revision: 24577
Versions of relevant libraries:
[pip3] flake8==7.1.1
[pip3] mypy==1.14.0
[pip3] mypy_extensions==1.0.0
[pip3] numpy==1.26.4
[pip3] numpydoc==1.8.0
[pip3] torch==2.6.0.dev20241231+cu118
[pip3] torchvision==0.22.0.dev20241230+cu118
[conda] _anaconda_depends 2024.10 py312_mkl_0
[conda] blas 1.0 mkl
[conda] mkl 2023.2.0 h6a75c08_49573 conda-forge
[conda] mkl-service 2.4.1 py312h0ad82dd_1 conda-forge
[conda] mkl_fft 1.3.10 py312h98b3aff_1 conda-forge
[conda] mkl_random 1.2.8 py312hb562361_0 conda-forge
[conda] numpy 1.26.4 py312hfd52020_0
[conda] numpy-base 1.26.4 py312h4dde369_0
[conda] numpydoc 1.8.0 pyhd8ed1ab_1 conda-forge
[conda] torch 2.6.0.dev20241231+cu118 pypi_0 pypi
[conda] torchvision 0.22.0.dev20241230+cu118 pypi_0 pypi
cc @csarofeen @ptrblck @xwang233 @eqy @msaroufim | module: cudnn,module: cuda,triaged | low | Critical |
2,765,242,664 | go | go/packages: line directives not treatead properly in the exported file | Reproducer (using the `x/tools/go/packages` testing API):
```go
func TestReproducer(t *testing.T) {
exported := packagestest.Export(t, packagestest.Modules, []packagestest.Module{
{
Name: "test",
Files: map[string]any{
"test.go": `package test; import "test/other"; var _ = other.Test;`,
"other/file.go": `package other
//line other.go:1:1
var Test int
`,
},
},
})
t.Cleanup(exported.Cleanup)
exported.Config.Mode = packages.LoadSyntax
exported.Config.Fset = token.NewFileSet()
pkgs, err := packages.Load(exported.Config, "test")
if err != nil {
t.Fatal(err)
}
packages.PrintErrors(pkgs)
p := pkgs[0].Imports["test/other"]
pos := p.Types.Scope().Lookup("Test").Pos()
t.Log(exported.Config.Fset.Position(pos)) // other.go:4:1
}
```
The `Mode` is set to `packages.LoadSyntax`, thus `go/packages` is going to load `test/other` from the `ExportFile`.
```bash
$ go test ./go/packages/ -run TestReproducer -v
=== RUN TestReproducer
(....)
packages_test.go:3455: other.go:4:1
--- PASS: TestReproducer (0.15s)
```
The file name (`other.go`) comes from the line directive, but the line/col (`4:1`) information does not.
I think that the issue is somewhere in `cmd/go`, while debugging, i saw the same values here (i.e. other.go:4:1):
https://github.com/golang/tools/blob/4f820dbaf9859eaafa01a17d133583f4d8c5a73c/internal/gcimporter/ureader_yes.go#L201-L205 | NeedsInvestigation | low | Critical |
2,765,254,426 | PowerToys | Bluetooth widget/floating window that shows battery information | ### Description of the new feature / enhancement
A floating window/widget for viewing Bluetooth devices battery percentage.
Windows currently doesn't have the option to open a floating Always-On-Top small window for viewing information about Bluetooth info.
A small floating window could be very nice (and easy) thing to have.
Plus it can notify you when the battery is at a low percentage :)
This is a very basic thing and its sad that windows does not have this already...
### Scenario when this would be used?
Showing the battery info for a Bluetooth headset for example. This could be helpful to know when to plug in the headset and not run out of battery.
### Supporting information
_No response_ | Needs-Triage | low | Minor |
2,765,258,545 | rust | "implementation of `Fn` is not general enough" on some conditions when using closures | Hello rust team!
I crossed the following compiler error.
There is a lifetime elision problem on closures on some specific conditions
- they accept as input a struct with a lifetime
- they are transmited to a function accepting multiple of them as generics
Quite hard to explain with words, so here is the simplified example:
## The code:
```rust
pub struct InodeMapper;
pub struct ValueCreatorParams<'a> {
pub child_name: &'a u32,
}
impl InodeMapper {
pub fn batch_insert<F, G>(
&self,
f1: F,
f2: G
)
where
F: for <'a> Fn(ValueCreatorParams<'a>) -> u32,
G: for <'b> Fn(ValueCreatorParams<'b>) -> i32
{
todo!()
}
}
fn test_batch_insert_large_entries_varying_depths() {
let mapper = InodeMapper{};
let f1 = |_| 1;
let f2 = |_| 2;
// *** ERROR ON FOLLOWING LINE ***
mapper.batch_insert(f1, f2);
}
```
## The error
```text
implementation of `Fn` is not general enough
closure with signature `fn(test::ValueCreatorParams<'2>) -> u32` must implement `Fn<(test::ValueCreatorParams<'1>,)>`, for any lifetime `'1`...
...but it actually implements `Fn<(test::ValueCreatorParams<'2>,)>`, for some specific lifetime `'2`rustc[Click for full compiler diagnostic](rust-analyzer-diagnostics-view:/diagnostic%20message%20[4]?4#file:///home/alogani/Coding/easy_fuser/src/types/test.rs)
implementation of `FnOnce` is not general enough
closure with signature `fn(test::ValueCreatorParams<'2>) -> u32` must implement `FnOnce<(test::ValueCreatorParams<'1>,)>`, for any lifetime `'1`...
...but it actually implements `FnOnce<(test::ValueCreatorParams<'2>,)>`, for some specific lifetime `'2`rustc[Click for full compiler diagnostic](rust-analyzer-diagnostics-view:/diagnostic%20message%20[5]?5#file:///home/alogani/Coding/easy_fuser/src/types/test.rs)
```
## The solution:
Fully qualify the types of the closure arguments (for both)!
```rust
fn test_batch_insert_large_entries_varying_depths() {
let mapper = InodeMapper{};
let f1 = |_: ValueCreatorParams| 1;
let f2 = |_: ValueCreatorParams| 2;
mapper.batch_insert(f1, f2);
}
```
And now it works like a charm !
### Meta
`rustc --version --verbose`:
```
rustc 1.82.0 (f6e511eec 2024-10-15)
binary: rustc
commit-hash: f6e511eec7342f59a25f7c0534f1dbea00d01b14
commit-date: 2024-10-15
host: x86_64-unknown-linux-gnu
release: 1.82.0
LLVM version: 19.1.1
```
## Suggestions
Obviously, it has a solution, but I fill the bug report, because:
- this is a situation where I don't understand why the compiler can't infer the lifetime. (Maybe there is a reason a good reason and it shall not be corrected? To be honest, I am not sure to understand the intrinsics)
- the error is not explicit (it took me several hours to isolate correctly the cause of the problem in my more complex codebase, I thought the problem were on signatures of the receiving function). So is there an improvement possible on compiler message ? Especially the compiler don't say how it infers a different lifetime for the two closures to help resolve the problem.
Thanks! | A-diagnostics,A-lifetimes,T-compiler,C-bug,needs-triage | low | Critical |
2,765,274,974 | godot | Android export from android will not update main scene layout unless .godot/exported/... is deleted | <!-- Failed to upload "repro-godotatoaexportedcache2.zip" -->
### Tested versions
- Reproducible on:
- Godot v4.4-dev7 - Android -> Android
- Godot master 0c45ace151f25de2ca54fe7a46b6f077be32ba6f - Android -> Android
- Godot master 2582793d408ade0b6ed42f913ae33e7da5fb9184 - Android -> Android
- Not Reproducible on:
- Godot 4.4-dev7 - Linux -> Android
- Godot 4.3-stable - Linux -> Android
- Godot master 2582793d408ade0b6ed42f913ae33e7da5fb9184 - Linux -> Android
- Godot 4.3-stable - Linux -> Linux
- Godot 4.4-dev7 - Linux -> Linux
- Godot 4.3-stable - Android -> Android (not implemented yet: https://github.com/godotengine/godot/commit/a5897d579bb0af496a18f7430345a67fe27ff0df)
### System information
Godot v4.4.dev7 - Android - Single-window, 1 monitor - Vulkan (Mobile) - integrated Mali-G715 - (9 threads)
(Google Pixel 8)
### Issue description
It looks like the scene is cached in `.godot/exported/<id>/file_cache` on the first export, which is not updated in subsequent exports....
~~It appears that the desktop editor does not create `.godot/exported/<id>/file_cache` when exporting!?~~
### Steps to reproduce
Create a simple app on the editor in android. Export the app and install (all on the same device 😙🤌) then adjust the main scene layout to something different.. and re-export.
In the MRP you can hide/show the TextRect named `HideMeThenReExport`
It seems like the scripts get updated but the scene contents don't change on the exported app.
Delete `.godot/exported/<id>/file_cache` and then re-export and the scene updates to the new layout.
### Minimal reproduction project (MRP)
[repro-godotatoaexportedcache2.zip](https://github.com/user-attachments/files/18286768/repro-godotatoaexportedcache2.zip)
---
**Bugsquad Edit:** Adding info from #99023
When I export an APK file, it always exports the first exported version.When I delete a folder called exported in the file manager, I can export the new version of the file again. It's just me. My friend is totally fine.And it seems that only the scene files and resource files will not be updated, the script will be updated. Not only did I save it several times, but I even deleted GODOT and tried again, with the same result.
| bug,platform:android,topic:editor,topic:export | low | Critical |
2,765,280,152 | rust | RPIT associated type lifetime bound is ignored | <!--
Thank you for filing a bug report! 🐛 Please provide a short summary of the bug,
along with any information you feel relevant to replicating the bug.
-->
I tried this code:
```rust
trait Foo<'x> {
type Out;
fn foo(self) -> Self::Out;
}
struct Bar;
impl<'x> Foo<'x> for Bar {
type Out = ();
fn foo(self) -> Self::Out {
todo!()
}
}
fn make_static_foo<'x>(_: &'x ()) -> impl Foo<'x, Out: 'static> {
Bar
}
fn assert_static<T: 'static>(_: T) {}
fn test() {
let local = ();
assert_static(make_static_foo(&local).foo());
}
```
I expect it to compile, but instead it gives the following error:
```
error[E0597]: `local` does not live long enough
--> src/lib.rs:23:35
|
22 | let local = ();
| ----- binding `local` declared here
23 | assert_static(make_static_foo(&local).foo());
| ----------------^^^^^^-
| | |
| | borrowed value does not live long enough
| argument requires that `local` is borrowed for `'static`
24 | }
| - `local` dropped here while still borrowed
```
It looks like the `Out: 'static` bound on `make_static_foo` is just ignored.
The issue sounds similar to #106684, but it is actually the opposite:
In this issue the bound is in the RPIT instead of in the trait definition.
### Meta
<!--
If you're using the stable version of the compiler, you should also check if the
bug also exists in the beta or nightly versions.
-->
`rustc --version --verbose`:
```
rustc 1.85.0-nightly (7f75bfa1a 2024-12-30)
binary: rustc
commit-hash: 7f75bfa1ad4e9a9d33a179a90603001515e91991
commit-date: 2024-12-30
host: x86_64-unknown-linux-gnu
release: 1.85.0-nightly
LLVM version: 19.1.6
```
Same happens on stable | A-lifetimes,A-associated-items,A-impl-trait,C-bug,S-has-mcve,T-types | low | Critical |
2,765,293,633 | godot | [Godot4.3][iOS Plugin][xcode 16.2] Could not build module 'Foundation' and standard cpp errors for iOS plugin | ### Tested versions
-Reproducible in the 4.3 branch.
### System information
Mac M4 - godot 4.3 - XCode 16.2
### Issue description
I'm trying to build a custom iOS plugin following [the steps here](https://docs.godotengine.org/en/stable/tutorials/platform/ios/ios_plugin.html#creating-an-ios-plugin) using XCode 16.2 and godot 4.3 (branch).
It fails to build the 'Foundation' module as well as the standard cpp classes. See screenshot below.
<img width="1624" alt="Image" src="https://github.com/user-attachments/assets/2c3542e7-77ae-4222-b762-d46909b56f6f" />
### Steps to reproduce
1. Have XCode 16.2
2. Checkout the [default iOS plugin template](https://github.com/naithar/godot_ios_plugin).
3. Switch godot sub-module to branch `4.3`.
4. build `godot` with `scons platform=ios target=template_debug generate_bundle=yes ios_simulator=yes`
5. Open plugin project
6. Update `Search Header Paths` to new paths (the default ones are outdated).
7. Build the library
### Minimal reproduction project (MRP)
Follow the [official steps](https://docs.godotengine.org/en/stable/tutorials/platform/ios/ios_plugin.html#creating-an-ios-plugin) for creating a plugin using the [default template](https://github.com/naithar/godot_ios_plugin). Only difference is using Godot 4.3 and XCode 16. | platform:ios,topic:plugin,needs testing | low | Critical |
2,765,301,121 | vscode | VSCode Windows Do Not Restore to Their Original Ubuntu Workspaces After Reboot | When using Ubuntu OS with multiple workspaces (e.g., 4 fixed screens that can be navigated to using the Windows key), applications like Brave Browser restore their windows to the exact workspace they were in before a system shutdown or unexpected closure.
However, VSCode does not behave the same way. If multiple VSCode windows are open across different Ubuntu workspaces and the system is restarted, all the VSCode windows are restored to the first workspace, instead of returning to their original workspaces.
This disrupts workflow organization and creates additional overhead for users to manually reassign VSCode windows to the appropriate workspaces.
### Requested Feature:
Implement a feature similar to Brave Browser that enables VSCode to remember and restore its windows to the same Ubuntu workspaces they were in before a shutdown or restart.
### Steps to Reproduce:
1. Open multiple VSCode windows and place each in a different Ubuntu workspace.
2. Restart or shut down the system.
3. After the system restarts, note that all restored VSCode windows appear in the first workspace instead of their original ones.
### Expected Behavior:
VSCode windows should restore to the same Ubuntu workspaces they were in before the restart or shutdown.
| feature-request,linux,workbench-window | low | Minor |
2,765,301,857 | pytorch | item() on DTensor only grabs the local tensor | ### 🐛 Describe the bug
An example of a tensor for which the local tensor is insufficient is a norm, which is sharded across many GPUs.
I have not run this testcase because I don't have a convenient 2-GPU system, but the correct print would be `8` (norm of the whole tensor), and I expect this to print `5.65 = 4sqrt(2)` (norm of half the tensor). `torchrun --standalone --nnodes=1 --nproc-per-node=2 dtensor_2nodes.py`
```
import torch
from torch.distributed._tensor import DTensor, Shard, Replicate, distribute_tensor, distribute_module, init_device_mesh
import os
import torch.distributed as dist
import datetime
import torch.nn as nn
import torch.nn.functional as F
world_size = int(os.getenv("WORLD_SIZE", None))
local_rank = int(os.getenv("LOCAL_RANK", None))
global_rank = int(os.getenv("RANK", None))
print(f"world_size: {world_size}, local_rank: {local_rank}, global_rank: {global_rank}")
dist.init_process_group(
backend="cuda:nccl",
init_method=None,
world_size=world_size,
rank=global_rank,
device_id=torch.device(f"cuda:{local_rank}"),
timeout=datetime.timedelta(seconds=120),
)
device_mesh = init_device_mesh("cuda", (2,))
rowwise_placement = [Shard(0)]
local_tensor = torch.randn((8, 8), requires_grad=True)
rowwise_tensor = DTensor.from_local(local_tensor, device_mesh, rowwise_placement)
print("correct would be 8, but it's probably 5.65", rowwise_tensor.norm().item())
```
### Versions
```
PyTorch version: 2.5.1
Is debug build: False
CUDA used to build PyTorch: 12.6
ROCM used to build PyTorch: N/A
OS: Ubuntu 22.04.5 LTS (x86_64)
GCC version: (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0
Clang version: Could not collect
CMake version: version 3.31.1
Libc version: glibc-2.35
Python version: 3.10.12 (main, Nov 6 2024, 20:22:13) [GCC 11.4.0] (64-bit runtime)
Python platform: Linux-6.5.13-650-3434-22042-coreweave-1-x86_64-with-glibc2.35
Is CUDA available: True
CUDA runtime version: 12.6.85
CUDA_MODULE_LOADING set to: LAZY
GPU models and configuration: GPU 0: NVIDIA H100 80GB HBM3
Nvidia driver version: 535.216.01
cuDNN version: Probably one of the following:
/usr/lib/x86_64-linux-gnu/libcudnn.so.9.5.1
/usr/lib/x86_64-linux-gnu/libcudnn_adv.so.9.5.1
/usr/lib/x86_64-linux-gnu/libcudnn_cnn.so.9.5.1
/usr/lib/x86_64-linux-gnu/libcudnn_engines_precompiled.so.9.5.1
/usr/lib/x86_64-linux-gnu/libcudnn_engines_runtime_compiled.so.9.5.1
/usr/lib/x86_64-linux-gnu/libcudnn_graph.so.9.5.1
/usr/lib/x86_64-linux-gnu/libcudnn_heuristic.so.9.5.1
/usr/lib/x86_64-linux-gnu/libcudnn_ops.so.9.5.1
HIP runtime version: N/A
MIOpen runtime version: N/A
Is XNNPACK available: True
CPU:
Architecture: x86_64
CPU op-mode(s): 32-bit, 64-bit
Address sizes: 46 bits physical, 57 bits virtual
Byte Order: Little Endian
CPU(s): 128
On-line CPU(s) list: 0-127
Vendor ID: GenuineIntel
Model name: Intel(R) Xeon(R) Platinum 8462Y+
CPU family: 6
Model: 143
Thread(s) per core: 2
Core(s) per socket: 32
Socket(s): 2
Stepping: 8
CPU max MHz: 4100.0000
CPU min MHz: 800.0000
BogoMIPS: 5600.00
Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf tsc_known_freq pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb cat_l3 cat_l2 cdp_l3 invpcid_single cdp_l2 ssbd mba ibrs ibpb stibp ibrs_enhanced tpr_shadow flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb intel_pt avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local split_lock_detect avx_vnni avx512_bf16 wbnoinvd dtherm ida arat pln pts hfi vnmi avx512vbmi umip pku ospke waitpkg avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg tme avx512_vpopcntdq la57 rdpid bus_lock_detect cldemote movdiri movdir64b enqcmd fsrm md_clear serialize tsxldtrk pconfig arch_lbr ibt amx_bf16 avx512_fp16 amx_tile amx_int8 flush_l1d arch_capabilities
Virtualization: VT-x
L1d cache: 3 MiB (64 instances)
L1i cache: 2 MiB (64 instances)
L2 cache: 128 MiB (64 instances)
L3 cache: 120 MiB (2 instances)
NUMA node(s): 2
NUMA node0 CPU(s): 0,2,4,6,8,10,12,14,16,18,20,22,24,26,28,30,32,34,36,38,40,42,44,46,48,50,52,54,56,58,60,62,64,66,68,70,72,74,76,78,80,82,84,86,88,90,92,94,96,98,100,102,104,106,108,110,112,114,116,118,120,122,124,126
NUMA node1 CPU(s): 1,3,5,7,9,11,13,15,17,19,21,23,25,27,29,31,33,35,37,39,41,43,45,47,49,51,53,55,57,59,61,63,65,67,69,71,73,75,77,79,81,83,85,87,89,91,93,95,97,99,101,103,105,107,109,111,113,115,117,119,121,123,125,127
Vulnerability Gather data sampling: Not affected
Vulnerability Itlb multihit: Not affected
Vulnerability L1tf: Not affected
Vulnerability Mds: Not affected
Vulnerability Meltdown: Not affected
Vulnerability Mmio stale data: Not affected
Vulnerability Retbleed: Not affected
Vulnerability Spec rstack overflow: Not affected
Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl
Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization
Vulnerability Spectre v2: Mitigation; Enhanced / Automatic IBRS; IBPB conditional; RSB filling; PBRSB-eIBRS SW sequence; BHI BHI_DIS_S
Vulnerability Srbds: Not affected
Vulnerability Tsx async abort: Not affected
Versions of relevant libraries:
[pip3] clip-anytorch==2.6.0
[pip3] dctorch==0.1.2
[pip3] DISTS-pytorch==0.1
[pip3] gpytorch==1.13
[pip3] lovely-numpy==0.2.13
[pip3] mypy-extensions==1.0.0
[pip3] numpy==1.24.4
[pip3] torch==2.5.1
[pip3] torchaudio==2.5.0
[pip3] torchdiffeq==0.2.5
[pip3] torchsde==0.2.6
[pip3] torchvision==0.20.0
[pip3] triton==3.1.0
[pip3] welford-torch==0.2.4
[conda] Could not collect
```
cc @H-Huang @awgu @kwen2501 @wanchaol @fegin @fduwjj @wz337 @wconstab @d4l3k @c-p-i-o @tianyu-l @XilunWu | oncall: distributed,triaged,module: dtensor | low | Critical |
2,765,308,781 | terminal | Implement kitty keyboard protocol | Spec: https://sw.kovidgoyal.net/kitty/keyboard-protocol/
Dup #11509
I just wanted to draw your attention to two new facts:
1) Since the Kitty protocol has [started being supported in iTerm2](https://gitlab.com/gnachman/iterm2/-/issues/10017), we can say that its independent implementation exists on all platforms except Windows. It seems to be gradually becoming a de facto technological standard.
2) A [patch with support for win32-input-mode](https://gitlab.gnome.org/GNOME/vte/-/issues/2601#note_2287197) has been written for the GNOME terminal. If you, like me, are interested in the development of the console applications ecosystem and improving their UX across all platforms, please express your support for its adoption. | Needs-Triage,Needs-Tag-Fix | low | Minor |
2,765,313,889 | neovim | presentation mode | # Problem
Various filetypes like markdown, latex, and other formats, have a "rendered" form which has a different layout or conceals parts of the text. Currently, this limits how fancy we can render these filetypes; we have to choose between optimizing for editing instead of viewing.
# Expected behavior
Introduce the concept of "presentation mode". This could be a simple flag or variable, which triggers filetype-specific handling.
- Can be easily toggled. Suggested mapping: `z<tab>`, or `<backspace>`, or ...?
- Disable when entering insert-mode?
- Filetype-specific handling:
- `text`: "flow" layout (soft-wrap)
- `markdown`: prettify headings/URLs/lists, "flow" layout (soft-wrap)
- `help` (vimdoc): prettify headings, "flow" layout (soft-wrap)
- Plugins are also encouraged to handle this mode. E.g. slides
- Set 'conceallevel' ?
- Vim has a `'readonly'` flag and related `:view` command. We could use this to signal "presentation mode"?
- Problem: 'readonly' is buffer-local, whereas presentation mode is presumably window-local... | enhancement,plugin,runtime,display,gsoc,options,editor | low | Major |
2,765,320,299 | vscode | Git - Saving/closing COMMIT_EDITMSG during a git commit randomly does not complete the commit |
Type: <b>Bug</b>
This is a random issue. I have not found a sequence that specificly makes this fail.
This issue is that when I use the editor's COMMIT_EDITMSG file to write my commit message, (click Commit button with and empty Message input) the message saves, but the commit does not complete.
The commit messages are usually somewhat extensive (several paragraphs). I review diffs of the files I'm committing as I write the commit message so I am in and out of focus on the file. But it has also happend when I simply paste a commit message in and immediately close the file.
I have tried several versions of closing out of the file to submit the commit:
- Save then close the file (I don't remember if I get a prompt in this case)
- Close (cmd-W or click the close button) the file and click the save button in the prompt
- Close (cmd-W or click the close button) the file and click enter to select the default (save) button in the prompt.
All three of these have successfully submitted the commit, and failed to do so. The edited content appears to save into `.git/COMMIT_EDITMSG`.
I have checked the git output and don't see any consistent error messages. There are lines that seem to be associated with commiting when the commit works, and they are simply missing when it doesn't. The only thing close to an error is when the commit works there are two similar warnings:
```
2025-01-01 17:44:08.866 [info] > git ls-files --stage -- /Users/trinkel/Development/DevOps/_Training/Kevin Powell/240922-HeadlessCMS.stack/.git/COMMIT_EDITMSG [27ms]
2025-01-01 17:44:08.866 [info] > git show --textconv :.git/COMMIT_EDITMSG [28ms]
2025-01-01 17:44:22.044 [info] > git -c user.useConfigOnly=true commit --quiet [15570ms]
2025-01-01 17:44:22.046 [info] [Git][getRemotes] No remotes found in the git config file
2025-01-01 17:44:22.077 [info] > git config --get commit.template [31ms]
2025-01-01 17:44:22.086 [info] > git for-each-ref --format=%(refname)%00%(upstream:short)%00%(objectname)%00%(upstream:track)%00%(upstream:remotename)%00%(upstream:remoteref) --ignore-case refs/heads/main refs/remotes/main [39ms]
2025-01-01 17:44:22.129 [info] > git status -z -uall [41ms]
2025-01-01 17:44:22.131 [info] > git for-each-ref --sort -committerdate --format %(refname) %(objectname) %(*objectname) [42ms]
2025-01-01 17:44:22.165 [info] > git config --local branch.main.github-pr-owner-number [29ms]
2025-01-01 17:44:22.166 [warning] [Git][config] git config failed: Failed to execute git
2025-01-01 17:44:22.182 [info] [Git][getRemotes] No remotes found in the git config file
2025-01-01 17:44:22.195 [info] > git config --local branch.main.remote [28ms]
2025-01-01 17:44:22.195 [warning] [Git][config] git config failed: Failed to execute git
2025-01-01 17:44:22.209 [info] > git config --get commit.template [28ms]
2025-01-01 17:44:22.213 [info] > git for-each-ref --format=%(refname)%00%(upstream:short)%00%(objectname)%00%(upstream:track)%00%(upstream:remotename)%00%(upstream:remoteref) --ignore-case refs/heads/main refs/remotes/main [31ms]
2025-01-01 17:44:22.216 [info] > git log --format=%H%n%aN%n%aE%n%at%n%ct%n%P%n%D%n%B -z --shortstat --diff-merges=first-parent -n50 --skip=0 --topo-order --decorate=full --stdin [75ms]
2025-01-01 17:44:22.257 [info] > git config --local branch.main.merge [61ms]
2025-01-01 17:44:22.258 [warning] [Git][config] git config failed: Failed to execute git
```
There is no upstream remote for this project. I have tried to clip out what seems to be the significant section of the logs for brevity, but have saved the all of the log if you need it.
VS Code version: Code 1.96.2 (Universal) (fabdb6a30b49f79a7aba0f2ad9df9b399473380f, 2024-12-19T10:22:47.216Z)
OS version: Darwin arm64 24.1.0
Modes:
<details>
<summary>System Info</summary>
|Item|Value|
|---|---|
|CPUs|Apple M1 Pro (10 x 2400)|
|GPU Status|2d_canvas: enabled<br>canvas_oop_rasterization: enabled_on<br>direct_rendering_display_compositor: disabled_off_ok<br>gpu_compositing: enabled<br>multiple_raster_threads: enabled_on<br>opengl: enabled_on<br>rasterization: enabled<br>raw_draw: disabled_off_ok<br>skia_graphite: disabled_off<br>video_decode: enabled<br>video_encode: enabled<br>webgl: enabled<br>webgl2: enabled<br>webgpu: enabled<br>webnn: disabled_off|
|Load (avg)|3, 3, 5|
|Memory (System)|16.00GB (0.08GB free)|
|Process Argv|--crash-reporter-id 9dc43c00-8bab-4a00-8174-e85d64b2a5cd|
|Screen Reader|yes|
|VM|0%|
</details><details><summary>Extensions (44)</summary>
Extension|Author (truncated)|Version
---|---|---
better-comments|aar|3.0.2
dark-synthwave-vscode|Aar|1.0.3
codewhisperer-for-command-line-companion|ama|1.5.1
astro-vscode|ast|2.15.4
vscode-intelephense-client|bme|1.12.6
vscode-toggle-quotes|Bri|0.3.6
vscode-zonefile|Com|0.0.4
jsdoc-generator|cry|2.2.0
postcss|css|1.0.9
vscode-eslint|dba|3.0.10
gitlens|eam|16.1.1
prettier-vscode|esb|11.0.0
nunjucks-template|ese|0.5.1
csv-editor|est|0.2.2
auto-rename-tag|for|0.1.10
code-runner|for|0.12.2
vscode-pull-request-github|Git|0.102.0
live-sass|gle|6.1.2
vscode-graphql-syntax|Gra|1.3.8
applescript|idl|0.26.1
vscode-edit-csv|jan|0.11.1
vscode-text-pastry|jkj|1.3.1
rainbow-csv|mec|3.13.0
pieces-vscode|Mes|2.0.0
git-graph|mhu|1.30.0
diff-merge|mos|0.7.0
vscode-scss|mrm|0.10.0
vscode-docker|ms-|1.29.3
remote-containers|ms-|0.394.0
remote-ssh|ms-|0.116.1
remote-ssh-edit|ms-|0.87.0
remote-explorer|ms-|0.4.3
laravel-blade|one|1.36.1
cssvar|pho|2.6.4
material-icon-theme|PKi|5.16.0
prisma|Pri|6.1.0
LiveServer|rit|5.7.9
vs-code-prettier-eslint|rve|6.0.0
code-spell-checker|str|4.0.21
svelte-vscode|sve|109.4.0
vscode-conventional-commits|viv|1.26.0
volar|Vue|2.2.0
vscode-postcss|vun|2.0.2
material-theme|zhu|3.17.7
(3 theme extensions excluded)
</details><details>
<summary>A/B Experiments</summary>
```
vsliv368cf:30146710
vspor879:30202332
vspor708:30202333
vspor363:30204092
vscod805cf:30301675
binariesv615:30325510
vsaa593:30376534
py29gd2263:31024239
c4g48928:30535728
azure-dev_surveyone:30548225
a9j8j154:30646983
962ge761:30959799
pythonnoceb:30805159
pythonmypyd1:30879173
h48ei257:31000450
pythontbext0:30879054
cppperfnew:31000557
dsvsc020:30976470
pythonait:31006305
dsvsc021:30996838
dvdeprecation:31068756
dwnewjupytercf:31046870
2f103344:31071589
nativerepl1:31139838
pythonrstrctxt:31112756
nativeloc2:31192216
cf971741:31144450
iacca1:31171482
notype1cf:31157160
5fd0e150:31155592
dwcopilot:31170013
stablechunks:31184530
6074i472:31201624
```
</details>
<!-- generated by issue reporter --> | bug,git | low | Critical |
2,765,338,395 | flutter | Remove or Continuously Update Flutter's GitHub Releases to Avoid Unnecessary Public Misunderstanding | ### Use case
The latest version is still showing as 2023, which creates a false impression that 'Flutter is dead' for those who only take a quick glance. Through a snowball effect, this misconception spreads to more people, and I have indeed seen quite a few people who hold this belief
### Proposal
Remove or Continuously Update Releases to Avoid Unnecessary Public Misconceptions | c: proposal,team-release | low | Minor |
2,765,340,100 | PowerToys | Keyboard Manager not allowing to SELECT combination of keys | ### Microsoft PowerToys version
0.87.1
### Installation method
PowerToys auto-update
### Running as admin
Yes
### Area(s) with issue?
Keyboard Manager
### Steps to reproduce
When Remapping a key, the **Select** button, to define the remap, will only accept one key at a time. You cannot press two keys ( **Alt (Right)** + **X**) to then define the remapping.
1. Open Remap keys
2. Click on **Add key remapping**
3. Click on **Select** OR 3.a. Use drop-down list and choose **Alt (Right)**
4. Select keys on the keyboard, i.e. **Alt (Right)** and **X** OR 4.a. No other drop-down list field is shown to define a key combination
### ✔️ Expected Behavior
Users should be able to click **Select** and tap on the keys they want to combine to set up the remapping.
### ❌ Actual Behavior
Only one key will be selected when the user presses **Alt (Right)** and **X** keys to define the **Select** keys.
I also tried this by pressing the two keys separately and simultaneously with no success.
In contrast, the Select on the To Send column works as expected (i.e. can select multiple keys to define a combination)
### Other Software
_No response_ | Issue-Bug,Product-Keyboard Shortcut Manager,Needs-Triage | low | Minor |
2,765,351,170 | kubernetes | async API call for NominatedNodeName and pod condition | Follow up: https://github.com/kubernetes/kubernetes/issues/126858#issuecomment-2344284869
/cc @JasonChen57 @kubernetes/sig-scheduling-leads @macsko @dom4ha
/assign
/kind feature
/sig scheduling
The scope of [KEP-4832](https://github.com/kubernetes/enhancements/issues/4832) is currently only the API calls made within the preemption plugin, which is for victim Pod deletion.
But, there's another API call involved to patch the unscheduled pod with nominated node name, status etc, which we may also want to do asynchronously.
https://github.com/kubernetes/kubernetes/blob/c3ebd95c837a21c0c79ab64721c28bba44331bf9/pkg/scheduler/schedule_one.go#L1100-L1107
We can see a potential perf improvement with scheduler-perf with a simple PoC, and decide whether we really want to do it or not.
Also, it has a broader blast radius since it impacts _all_ unschedulable pods, and hence may not be allowed to just add into the scope of KEP-4832...? I'm not sure. | sig/scheduling,kind/feature,needs-triage | low | Major |
2,765,354,040 | transformers | Request for a Vision Transformer Model for Digital Image Segmentation | ### Model description
I would like to request the addition of a Vision Transformer (ViT) model specifically fine-tuned for digital image segmentation tasks. The model should leverage transformer-based architecture to effectively capture spatial relationships within images, improving performance in tasks such as medical image analysis, satellite image segmentation, or autonomous driving.
The Vision Transformer architecture has proven to be highly effective for various vision tasks by using self-attention mechanisms to capture long-range dependencies in images. This model would be particularly valuable for tasks requiring pixel-level classification, where traditional convolutional neural networks (CNNs) often struggle to capture global features effectively.
The ViT model should include the following key features:
- Pretrained on a large, diverse image segmentation dataset.
- Fine-tuned for pixel-level classification tasks such as medical image segmentation or semantic segmentation of everyday objects.
- Support for standard ViT variants such as ViT-B (Base), ViT-L (Large), and ViT-H (Huge) depending on the task's computational budget.
- Open-source weights and implementation.
### Open source status
- [X] The model implementation is available
- [X] The model weights are available
### Provide useful links for the implementation
@amyeroberts, @qubvel | New model | low | Major |
2,765,357,258 | svelte | window onload does not fire up in chrome | ### Describe the bug
When i use `<svelte:window onload={onLoad}>` it does not work in chrome (And also not in svelte.dev environments), but it does work in Firefox.
After talking with chatgpt the fix was:
```
onMount(() => {
if (document.readyState === 'complete') {
onLoad();
} else {
// Otherwise, wait for the load event
window.addEventListener('load', onLoad, { once: true });
}
});
function onLoad(_event) {
console.debug('loaded window.');
isAppLoaded = true;
}
```
According to chatgpt onload event may fire before the sveltecode which attaches the eventhandler executes.
I am not a big expert in WebDev, but if I understand this correctly, it is not only a svelt issue. It would be nice if the <svelte window:onload> had already the fix above implmeneted, if that is even the correct way to handle that.
### Reproduction
https://svelte.dev/playground/0f493cd43f36479fb6c907fa08d16ed3?version=5.16.0
Currently, it is successfully reproduces in the online environemnt of svelte.dev, but due to the nature of the issue (race condition), there might be a chance it won't reproduce in the future.
### Logs
_No response_
### System Info
```shell
Independant Scripts:
Chromium (131.0.2903.99)
Internet Explorer: 11.0.26100.1882
npmPackages:
svelte: ^5.0.0 => 5.16.0
```
### Severity
annoyance | needs discussion | low | Critical |
2,765,396,195 | next.js | DeprecationWarning: The `util._extend` API is deprecated. Please use Object.assign() instead. | ### Link to the code that reproduces this issue
https://github.com/kuanjiahong/deprecation-warning-app
### To Reproduce
**Development mode**
1. Start the application in development `npm run dev`
2. Go to `http://localhost:3000`
3. Click the button to rewrite the url
4. Check the console for the deprecation warning
**Deployment - Node.js Server**
1. Build the application `npm run build`
2. Run the application `npm run start`
3. Go to `http://localhost:3000`
4. Click the button to rewrite the url
5. Check the console for the deprecation warning
**Deployment - Docker image**
1. Build container `docker build -t nextjs-docker .`
2. Run container: `docker run -p 3000:3000 nextjs-docker`
3. Go to `http://localhost:3000`
4. Click the button to rewrite the url
5. Check the console for the deprecation warning
### Current vs. Expected behavior
Current behaviour:
A deprecation warning is shown:
```bash
[DEP0060] DeprecationWarning: The `util._extend` API is deprecated. Please use Object.assign() instead.
(Use `node --trace-deprecation ...` to show where the warning was created)
```
When used node --trace-deprecation to show where the warning was created:
```
(node:1) [DEP0060] DeprecationWarning: The `util._extend` API is deprecated. Please use Object.assign() instead.
at ProxyServer.<anonymous> (/app/node_modules/next/dist/compiled/http-proxy/index.js:13:2607)
at proxyRequest (/app/node_modules/next/dist/server/lib/router-utils/proxy-request.js:108:15)
at handleRequest (/app/node_modules/next/dist/server/lib/router-server.js:332:61)
at process.processTicksAndRejections (node:internal/process/task_queues:105:5)
at async requestHandlerImpl (/app/node_modules/next/dist/server/lib/router-server.js:441:13)
at async Server.requestListener (/app/node_modules/next/dist/server/lib/start-server.js:155:13)
```
Expected behaviour:
No deprecation warning.
### Provide environment information
```bash
Operating System:
Platform: win32
Arch: x64
Version: Windows 10 Enterprise
Available memory (MB): 32562
Available CPU cores: 8
Binaries:
Node: 22.12.0
npm: 10.9.2
Yarn: N/A
pnpm: N/A
Relevant Packages:
next: 15.1.1-canary.23 // Latest available version is detected (15.1.1-canary.23).
eslint-config-next: N/A
react: 19.0.0
react-dom: 19.0.0
typescript: 5.3.3
Next.js Config:
output: standalone
```
### Which area(s) are affected? (Select all that apply)
Runtime
### Which stage(s) are affected? (Select all that apply)
next dev (local), next start (local), Other (Deployed)
### Additional context
I found these related issue: #72220 #71374
I found that this issue start to occur when using Node version >= 22.
This issue does not occur when using Node v20. | Runtime | low | Minor |
2,765,398,391 | deno | `node:crypto` implementation doesn't support ECDSA secp256k1 | Version: Deno 2.1.4
Related: https://github.com/denoland/deno/issues/24989#issuecomment-2567191851
Deno, with its `node:crypto` implementation, doesn't support doing ECDSA with secp256k1, only ECDH is supported (which is a different thing).
This code works on Node.js but throws on Deno:
```ts
import * as crypt from 'node:crypto';
crypt.generateKeyPair('ec', { namedCurve: 'secp256k1' }, console.log);
```
Used in [`@atcute/crypto`](https://github.com/mary-ext/atcute/tree/trunk/packages/utilities/crypto) to [validate most signatures in AT Protocol](https://atproto.com/specs/cryptography), as secp256k1 is more readily available in KMS/HSMs.
Currently, `@atcute/crypto` mitigates this lack of support by adding an [imports condition for Deno](https://github.com/mary-ext/atcute/blob/7fc523522bdd13c6562b06cf47ad87a715414743/packages/utilities/crypto/package.json#L28-L35), it would be nice if Deno actually supported this to avoid using the JS-based [`@noble/secp256k1`](https://github.com/paulmillr/noble-secp256k1) library for signing and verification. | bug,node compat,crypto | low | Minor |
2,765,426,633 | rust | Typesystem soundness hole involving cyclically-defined ATIT, and normalization in trait bounds | This isn't quite trivial, but well… it works.
a “transmute” in safe Rust:
```rust
fn main() {
let s: String = transmute(vec![65_u8, 66, 67]);
println!("{s}"); // ABC
}
```
```rust
fn transmute<L, R>(x: L) -> R {
transmute_inner_1::<L, R, RewriteReflRight<FakeRefl<L, R>>>(x)
}
fn transmute_inner_1<L, R, P: TyEq<LHS = L, RHS = R>>(x: L) -> R {
transmute_inner_2::<<P::ProofIsProofValue as TyEq>::ProofDef, L, R, P::ProofValue, P>(x)
}
fn transmute_inner_2<Rw, L, R, Actual, P: TyEq<LHS = L, RHS = R, ProofValue = Actual>>(x: L) -> R
where
<Rw as TypeIs<P::ProofValue>>::Is: TyEq<LHS = L, RHS = R>,
{
transmute_inner_3::<L, R, Actual>(x)
}
fn transmute_inner_3<L, R, P: TyEq<LHS = L, RHS = R>>(x: L) -> R {
transmute_inner_4::<R, P::ProofDef>(x)
}
fn transmute_inner_4<R, Rw>(x: <Rw as TypeIs<R>>::Is) -> R {
x
}
```
```rust
trait TypeIs<T> {
type Is;
}
impl<_Self, T> TypeIs<T> for _Self {
type Is = T;
}
trait TyEq: TyEqImpl {
type ProofDef: TypeIs<Self::RHS, Is = Self::LHS>;
}
trait TyEqImpl {
type LHS;
type RHS;
type Proof<_Dummy>: TyEq<LHS = Self::LHS, RHS = Self::RHS>;
type ProofValue;
type ProofIsProofValue: TyEq<LHS = Self::Proof<()>, RHS = Self::ProofValue>;
}
trait DeriveEqFromImpl {}
impl<P: TyEqImpl + DeriveEqFromImpl> TyEq for P {
type ProofDef = <P::Proof<()> as TyEq>::ProofDef;
}
struct Refl<T>(T);
impl<T> TyEqImpl for Refl<T> {
type LHS = T;
type RHS = T;
type Proof<_Dummy> = Refl<T>;
type ProofValue = Refl<T>;
type ProofIsProofValue = Refl<Refl<T>>;
}
impl<T> TyEq for Refl<T> {
type ProofDef = ();
}
struct FakeRefl<L, R>(L, R);
impl<L, R> DeriveEqFromImpl for FakeRefl<L, R> {}
impl<L, R> TyEqImpl for FakeRefl<L, R> {
type LHS = L;
type RHS = R;
type Proof<_Dummy> = FakeRefl<L, R>;
type ProofValue = FakeRefl<L, R>;
type ProofIsProofValue = Refl<FakeRefl<L, R>>;
}
struct RewriteReflRight<P>(P);
impl<P> DeriveEqFromImpl for RewriteReflRight<P> {}
impl<P, L, R> TyEqImpl for RewriteReflRight<P>
where
P: TyEq<LHS = L, RHS = R>,
{
type LHS = L;
type RHS = R;
type Proof<_Dummy: RewriteReflRightHelper> = _Dummy::RewriteRight<Refl<L>, R, P::ProofDef>;
type ProofValue = Refl<L>;
type ProofIsProofValue = Refl<Refl<L>>;
}
trait RewriteReflRightHelper {
type RewriteRight<P, R, Rw>: TyEq<LHS = P::LHS, RHS = R>
where
P: TyEq<RHS = <Rw as TypeIs<R>>::Is>;
}
impl<_Dummy> RewriteReflRightHelper for _Dummy {
type RewriteRight<P, R, Rw>
= P
where
P: TyEq<RHS = <Rw as TypeIs<R>>::Is>;
}
```
([playground](https://play.rust-lang.org/?version=stable&mode=debug&edition=2021&gist=4b187258e5a6e000417190f0f14a1ec0))
Besides this unsoundness, there are [also many ICEs](https://play.rust-lang.org/?version=stable&mode=debug&edition=2021&gist=304c247937ece5930ec548a5a479256e). This isn't surprising, since we're not *really* transmuting, but rather sort-of … convincing the type system that the 2 types were never different in the first place.
```rust
fn main() {
let s: u8 = transmute(());
println!("{s:?}");
}
```
Or interesting LLVM-errors
```rust
fn main() {
let s: &() = transmute("hi");
println!("{s:?}");
}
```
```
Compiling playground v0.0.1 (/playground)
Invalid bitcast
%7 = bitcast { ptr, i64 } %6 to ptr, !dbg !425
in function _ZN10playground17transmute_inner_317h363424402e6a7153E
rustc-LLVM ERROR: Broken function found, compilation aborted!
error: could not compile `playground` (bin "playground")
```
Oh… [that one on nightly has… the compiler itself execute a SIGILL](https://play.rust-lang.org/?version=nightly&mode=debug&edition=2021&gist=54c7da3065e4d042f121662122cd3ffd)? (Is that actual UB in the compiler!? Or UB in LLVM? Or can SIGILL be part of a *deliberate* crash condition?)
---
From a background of “this works a bit like Coq”, the relevant parts that make this work is how:
* `FakeRefl<L, R>` is a “proof” that `L` and `R` are the same types, which doesn't terminate (i.e. it is cyclically defined in terms of itself)
* unlike true proof assistants, Rust's trait system does allow some stuff to be defined in a somewhat cyclical manner, especially pre-monomorphization
* overflow during monomorphization is avoided anyways by:
* introducing the `Rewrite…` step which rewrites `Refl<L>` (a proof of `TyEq<LHS = L, RHS = R>`) using this `FakeRefl` proof
* at the same time *also* tracking that the proof term itself doesn't actually change with the rewrite
* using this tracked meta-information in order to eliminate the usage of `FakeRefl` before its (indirectly and cyclically defined) `ProofDef` type ever ends up being instantiated
Of course, this is just my intuitive description from a user perspective :-)
---
I have no idea which part of this code to blame exactly. Perhaps someone else with better knowledge of the theory behind Rust's typesystem and trait system could have a better clue here.
~~I'm not quite sure if~~ this can perhaps be "simplified" to remove the need for GATs
**Update**: It *can* be "simplified" to remove the need for GATs. ([playground](https://play.rust-lang.org/?version=stable&mode=debug&edition=2021&gist=48cfb42cae4b059efa1cccf7f991b337))
**Update2**: It's [even possible](https://github.com/rust-lang/rust/issues/135011#issuecomment-2569925948) to rework this into working since Rust 1.1
<details><summary><i>(this section has become somewhat outdated due to this update, click to expand anyway)</i></summary>
I'm not quite sure if this can perhaps be "simplified" to remove the need for GATs; however, I wasn't able to the `Rewrite…` stuff to work without this trick
```rust
type Proof<_Dummy: RewriteReflRightHelper> = _Dummy::RewriteRight<Refl<L>, R, P::ProofDef>;
```
where the (vacuous) `_Dummy: RewriteReflRightHelper` restriction prevents the compiler from already knowing the concrete `RewriteReflRightHelper` impl. (If you worry about the syntactical mismatch of
```rust
type Proof<_Dummy: RewriteReflRightHelper>
```
here vs
```rust
type Proof<_Dummy>: TyEq<LHS = Self::LHS, RHS = Self::RHS>;
```
without bounds on `_Dummy` in the trait definition: that's [actually avoidable](https://play.rust-lang.org/?version=stable&mode=debug&edition=2021&gist=a8257758d8535f11dc9553456f809be7) (<- see this playground on how the bound can be repeated everywhere and the `impl RewriteReflRightHelper for …` can even be for a concrete type only).
So for now, I would conjecture that this soundness hole *does* require GATs.
*Edit:* I completely forgot about the (generous) usage of GATs *inside* of `RewriteReflRightHelper` ~ so, yes, GATs seem fairly integral to this.
*Edit2:* Nevermind, those [can all be eliminated](https://play.rust-lang.org/?version=stable&mode=debug&edition=2021&gist=55294bcb7b83a8f934a4180cab390099) leaving only a single GAT.
*(end of somewhat outdated section)*
</details>
---
This is not a regression. It also isn't influenced by `-Znext-solver`.
---
This is a relatively clean typesystem hole, on stable Rust, without many of the other known-problematic features such as HRTBs, lifetimes, variance, trait objects, or implicitly defined trait impls for functions/closures/etc…
@rustbot label I-unsound, I-ICE, I-crash, T-types, A-type-system, A-trait-system, A-associated-items | A-type-system,I-crash,I-ICE,A-trait-system,P-medium,A-associated-items,I-unsound,C-bug,T-types | high | Critical |
2,765,435,794 | ui | [bug]: Chart Legend Vertical | ### Describe the bug
Layout prop is being ignored in the ChartLegend component.
### Affected component/components
Chart
### How to reproduce
<ChartLegend content={<ChartLegendContent nameKey="category" />} layout='vertical' verticalAlign='middle' align="right"/>
### Codesandbox/StackBlitz link
_No response_
### Logs
_No response_
### System Info
```bash
Firefox
Windows
Next 15+React19
```
### Before submitting
- [X] I've made research efforts and searched the documentation
- [X] I've searched for existing issues | bug | low | Critical |
2,765,448,583 | react | Bug: Wrong address for empty string message | ### Steps to reproduce
I don't know where the problem could be. Therefore I can't create an MRE.
This is a video I captured:
https://github.com/user-attachments/assets/1c21e144-2ccc-4fce-84af-2af15b8fe0b8
The point is, the message complaints that:
> An empty string ("") was passed to the src attribute. This may cause the browser to download the whole page again over the network. To fix this, either do not render the element at all or pass null to src instead of an empty string.
When I open that message to see the stack, it guides me to a component of mine called `ToggleView` and the line specified contains this code:
setViewStyle("cards")
And the `ToggleView.jsx` does not contain `src` attribute at all in it. Of course, I have `src` in many other places. But how can I know which one is causing the problem? The address is wrong.
### Current behavior
React provides misleading addresses that do not help at all in finding the problem, and litters the console for long time until we find the problem accidentally or through heuristics (trial & error).
### Expected behavior
React should provide accurate addresses.
### Your environment
```
System:
OS: Linux 6.8 Debian GNU/Linux 12 (bookworm) 12 (bookworm)
Binaries:
Node: 22.12.0 - /usr/local/bin/node
npm: 11.0.0 - /usr/local/bin/npm
Browsers:
Firefox: 133.0.3 (64-bit)
npmPackages:
react: ^19.0.0 => 19.0.0
react-dom: ^19.0.0 => 19.0.0
```
| Status: Unconfirmed | low | Critical |
2,765,455,946 | ui | [bug]: Chart Legend Each child in a list should have a unique "key" prop. | ### Describe the bug
```
"use client";
import { Card, CardContent, CardHeader, CardTitle } from "@/components/ui/card";
import {
ChartContainer,
ChartTooltip,
ChartTooltipContent,
ChartConfig,
ChartLegend,
ChartLegendContent
} from "@/components/ui/chart";
import {
PolarAngleAxis,
PolarGrid,
RadialBar,
RadialBarChart,
ResponsiveContainer,
} from "recharts";
import { Tractor, GraduationCap, Trees, Stethoscope, Home, Building2, HelpCircle, Factory, Droplets, Train } from 'lucide-react';
const data = [
{
SAL_CODE_2021: 13615,
MB_CATEGORY_2021: "Transport",
SAL_NAME_2021: "South Wentworthville",
AREA_SQM: 0.17,
},
{
SAL_CODE_2021: 13615,
MB_CATEGORY_2021: "Commercial",
SAL_NAME_2021: "South Wentworthville",
AREA_SQM: 0.04,
},
{
SAL_CODE_2021: 13615,
MB_CATEGORY_2021: "Parkland",
SAL_NAME_2021: "South Wentworthville",
AREA_SQM: 0.05,
},
{
SAL_CODE_2021: 13615,
MB_CATEGORY_2021: "Residential",
SAL_NAME_2021: "South Wentworthville",
AREA_SQM: 1.55,
},
];
const categoryIcons = {
"Primary Production": Tractor,
Education: GraduationCap,
Parkland: Trees,
"Hospital/Medical": Stethoscope,
Residential: Home,
Commercial: Building2,
Other: HelpCircle,
Industrial: Factory,
Water: Droplets,
Transport: Train,
};
const muted_colors = [
"hsl(var(--chart-1))",
"hsl(var(--chart-2))",
"hsl(var(--chart-3))",
"hsl(var(--chart-4))",
"hsl(var(--chart-5))",
];
export default function AreaBreakdown() {
const totalArea = data.reduce((sum, item) => sum + item.AREA_SQM, 0);
const chartData = data.map((item, index) => ({
category: item.MB_CATEGORY_2021,
SQM: item.AREA_SQM,
fill: muted_colors[index % muted_colors.length],
icon:
categoryIcons[item.MB_CATEGORY_2021 as keyof typeof categoryIcons] ||
HelpCircle,
}));
const chartConfig: ChartConfig = {
...Object.fromEntries(
data.map((item, index) => [
item.MB_CATEGORY_2021,
{
label: item.MB_CATEGORY_2021,
color: muted_colors[index % muted_colors.length],
value: item.AREA_SQM,
}
])
)
};
return (
<div className="w-full max-w-4xl mx-auto p-4 space-y-4">
<Card className="w-full">
<CardHeader>
<CardTitle>Area Breakdown - {data[0].SAL_NAME_2021}</CardTitle>
</CardHeader>
<CardContent className="pt-6">
<ChartContainer
config={chartConfig}
className="h-[400px]"
>
<ResponsiveContainer width="100%" height="100%">
<RadialBarChart
innerRadius="10%"
outerRadius="80%"
data={chartData}
startAngle={90}
endAngle={-180}
>
<PolarGrid gridType="circle" />
<PolarAngleAxis
type="number"
domain={[0, "auto"]}
tick={false}
/>
<RadialBar
label={{
position: "end",
// fill: "#888",
fontSize: 12,
formatter: (value: number) => `${value.toFixed(2)} sqm`
}}
cornerRadius={25}
dataKey="SQM"
/>
<ChartLegend content={<ChartLegendContent nameKey="category" />} />
<ChartTooltip
content={<ChartTooltipContent labelKey="SQM" nameKey="category"/>}
/>
</RadialBarChart>
</ResponsiveContainer>
</ChartContainer>
</CardContent>
</Card>
</div>
);
}
```
### Affected component/components
charts
### How to reproduce
<ChartLegend content={<ChartLegendContent nameKey="category" />} />
### Codesandbox/StackBlitz link
_No response_
### Logs
_No response_
### System Info
```bash
Nextjs15+React19
Windows
```
### Before submitting
- [X] I've made research efforts and searched the documentation
- [X] I've searched for existing issues | bug | low | Critical |
2,765,503,638 | godot | AnimatedSprite2D can call `queue_free()` in the editor in response to a signal without a tool script | ### Tested versions
- Reproducable in 4.4.dev7, 4.3.stable, 4.0.4.stable, 3.6.stable
### System information
Fedora Linux 41
### Issue description
An AnimatedSprite2D node with an `animation_finished` signal linked to `queue_free()` on any node will actually shoot that signal off in the editor and delete the node from the scene tree in the editor, even without a tool script (or even any script) involved. If this method is specified on the root of the scene, it will crash the entire editor.
If you instead attach to a script and link to a receiver method in that script, the removal does not happen. It only happens if you link directly to `queue_free()`, as far as I've been able to reproduce.
### Steps to reproduce
* Open a fresh project
* Create a Node2D
* Create a child AnimatedSprite2D and select it
* Go to the Node panel, and double-click on `animation_finished`
* Click "AnimatedSprite2D (Connecting From)"
* Change the "Receiver Method" to `queue_free`
* Click Connect
* Go to the Inspector panel
* Create a new SpriteFrames
* Add an empty frame to the `default` animation (there must be at least one frame, but it doesn't have to be empty)
* Disable looping on the `default` animation
* Press play
* Watch the sprite disappear from the tree when the animation finishes
### Minimal reproduction project (MRP)
This reproduction project has a DoesNotRemoveSelf node and a RemovesSelf node showing the behaviors. DoesNotRemoveSelf's signal calls `queue_free()` through an attached script, which does not cause any issues. RemovesSelf's signal calls `queue_free()` directly. Select RemovesSelf and click Play to see it free itself in the editor.
[queue_free-bug.zip](https://github.com/user-attachments/files/18288292/queue_free-bug.zip)
| bug,topic:editor | low | Critical |
2,765,509,638 | PowerToys | Ability to fix long paths (Alternative to Long Path Tool) | ### Description of the new feature / enhancement
I'm expecting a feature that would allow users to more-easily fix issues that arise with having files (and folders?) with long paths.
- Renaming the file
- Renaming the file path itself (maybe even the specified (nested) folder(s)
- Moving the file elsewhere
### Scenario when this would be used?
This would be very useful for when explorer _breaks_ and you can't manually rename a file. Currently, I have a file with a long file name and I noticed now that I can't rename the file to be shorter because anytime I try to rename it, it reverts right back to the original file path. Inspecting the file properties shows that the location prefix is `\\?\G:` and looking into it seems to be because of a broken long file path.
### Supporting information
I tried doing `ren "\\?\G:\folder\folder 2\long-file-name" "new-file-name"` and I was able to finally rename the file. Would be nice if I could do this with PowerTools instead. Perhaps the tool can automatically find broken file paths inside a specified directory and attempt to rename the files for you with similar options to the file rename tool. | Idea-New PowerToy,Needs-Triage | low | Critical |
2,765,527,366 | flutter | Request for documentation on configuration options, “backfill” | ### Type of Request
infra task
### Infrastructure Environment
Regarding ci.yaml
https://github.com/flutter/flutter/blob/d9b7e5664604a55a3e900b0c619ee319065abb0e/.ci.yaml#L591
I think this needs more context to clarify impact and effects of this setting. The entire configuration file is quite massive as are the dependencies, testing frameworks, code base, etc. I'll attempt to try to put some thought into it because this project is pretty major, but any explanations would be appreciated, thanks!
### Steps to reproduce
Step 1:
Step 2:
..
Step n:
### Expected results
I would like to request more information or comments to understand configuration. | team-infra | low | Minor |
2,765,539,630 | rust | `tests/ui/asan-odr-win/asan_odr_windows.rs` fails on native `x86_64-pc-windows-msvc` with `lld = true` + `use-lld = true` | On:
- Native `x86_64-pc-windows-msvc`
- Latest master at the time of writing, commit hash c528b8c6789
The test [`tests/ui/asan-odr-win/asan_odr_windows.rs`](https://github.com/rust-lang/rust/blob/c528b8c67895bfe7fdcdfeb56ec5bf6ef928dcd7/tests/ui/asan-odr-win/asan_odr_windows.rs) fails for me locally if I set `rust.lld = true` and `rust.use-lld = true`
```rs
[rust]
lld = true
use-lld = true
```
due to
```
note: lld: error: could not open 'X:\repos\rust\build\x86_64-pc-windows-msvc\stage1\lib\rustlib\x86_64-pc-windows-msvc\lib\librustc-dev_rt.asan.a': no such file or directory
```
Full test failure output:
<details>
<summary>Full test failure</summary>
```
---- [ui] tests\ui\asan-odr-win\asan_odr_windows.rs stdout ----
error: test compilation failed although it shouldn't!
status: exit code: 1
command: PATH="X:\repos\rust\build\x86_64-pc-windows-msvc\stage1\bin;C:\Program Files (x86)\Windows Kits\10\bin\x64;C:\Program Files (x86)\Windows Kits\10\bin\10.0.26100.0\x64;C:\Program Files (x86)\Microsoft Visual Studio\2022\BuildTools\VC\Tools\MSVC\14.43.34604\bin\HostX64\x64;C:\Program Files (x86)\Microsoft Visual Studio\2022\BuildTools\VC\Tools\MSVC\14.43.34604\bin\HostX64\x64;X:\repos\rust\build\x86_64-pc-windows-msvc\stage0-bootstrap-tools\x86_64-pc-windows-msvc\release\deps;X:\repos\rust\build\x86_64-pc-windows-msvc\stage0\bin;C:\Program Files\PowerShell\7;C:\Users\Administrator\AppData\Local\Programs\Python\Python312\Scripts\;C:\Users\Administrator\AppData\Local\Programs\Python\Python312\;C:\Program Files (x86)\Microsoft Visual Studio\2022\BuildTools\VC\Tools\MSVC\14.41.34120\bin\Hostx64\x64\;C:\Program Files\Alacritty\;C:\WINDOWS\system32;C:\WINDOWS;C:\WINDOWS\System32\Wbem;C:\WINDOWS\System32\WindowsPowerShell\v1.0\;C:\WINDOWS\System32\OpenSSH\;C:\Program Files (x86)\NVIDIA Corporation\PhysX\Common;C:\Program Files\dotnet\;C:\Program Files\Meld\;C:\Program Files (x86)\Lua\5.1;C:\Program Files (x86)\Lua\5.1\clibs;C:\Program Files\clang+llvm-18.1.6-x86_64-pc-windows-msvc\bin;C:\Program Files\WireGuard\;C:\Program Files\Mullvad VPN\resources;C:\Program Files\Graphviz\bin;C:\ProgramData\chocolatey\bin;C:\Program Files\Docker\Docker\resources\bin;C:\Program Files\GitHub CLI\;C:\Program Files\Neovim\bin;C:\Program Files\NVIDIA Corporation\NVIDIA app\NvDLISR;C:\Program Files\WezTerm;C:\Program Files\Microsoft VS Code\bin;C:\Program Files\Git\cmd;C:\Program Files\PowerShell\7\;C:\Program Files (x86)\Windows Kits\10\Windows Performance Toolkit\;C:\Users\Administrator\.cargo\bin;C:\Users\Administrator\AppData\Local\Programs\Python\Launcher\;C:\Users\Administrator\AppData\Local\Programs\Python\Python310\Scripts\;C:\Users\Administrator\AppData\Local\Programs\Python\Python310\;C:\Users\Administrator\AppData\Local\Programs\Python\Python312\Scripts\;C:\Users\Administrator\AppData\Local\Programs\Python\Python312\;C:\Users\Administrator\scoop\shims;C:\Users\Administrator\AppData\Local\Microsoft\WindowsApps;C:\Users\Administrator\AppData\Local\GitHubDesktop\bin;C:\Users\Administrator\AppData\Local\Microsoft\WinGet\Packages\ajeetdsouza.zoxide_Microsoft.Winget.Source_8wekyb3d8bbwe;C:\Users\Administrator\AppData\Local\Microsoft\WinGet\Packages\junegunn.fzf_Microsoft.Winget.Source_8wekyb3d8bbwe;C:\Program Files\Neovim\bin;C:\Users\Administrator\AppData\Local\Microsoft\WinGet\Packages\BurntSushi.ripgrep.MSVC_Microsoft.Winget.Source_8wekyb3d8bbwe\ripgrep-14.1.0-x86_64-pc-windows-msvc;C:\Program Files (x86)\Lua\5.1;C:\Program Files (x86)\LuaRocks;C:\Program Files (x86)\Lua\5.1\systree\bin;C:\Users\Administrator\AppData\Local\LuaRocks\bin;C:\Program Files\clang+llvm-18.1.6-x86_64-pc-windows-msvc\bin;C:\Users\Administrator\AppData\Local\Microsoft\WinGet\Links;C:\Program Files\JetBrains\RustRover 2024.2\bin;;C:\Program Files\Git;C:\Program Files (x86)\Windows Kits\10\Debuggers\x64;C:\Users\Administrator\bin" "X:\\repos\\rust\\build\\x86_64-pc-windows-msvc\\stage1\\bin\\rustc.exe" "X:\\repos\\rust\\tests\\ui\\asan-odr-win\\asan_odr_windows.rs" "-Zthreads=1" "-Zsimulate-remapped-rust-src-base=/rustc/FAKE_PREFIX" "-Ztranslate-remapped-path-to-local-path=no" "-Z" "ignore-directory-in-diagnostics-source-blocks=C:\\Users\\Administrator\\.cargo" "-Z" "ignore-directory-in-diagnostics-source-blocks=X:\\repos\\rust\\vendor" "--sysroot" "X:\\repos\\rust\\build\\x86_64-pc-windows-msvc\\stage1" "--target=x86_64-pc-windows-msvc" "--check-cfg" "cfg(FALSE)" "-O" "--error-format" "json" "--json" "future-incompat" "-Ccodegen-units=1" "-Zui-testing" "-Zdeduplicate-diagnostics=no" "-Zwrite-long-types-to-disk=no" "-Cstrip=debuginfo" "-C" "prefer-dynamic" "-o" "X:\\repos\\rust\\build\\x86_64-pc-windows-msvc\\test\\ui\\asan-odr-win\\asan_odr_windows\\a.exe" "-A" "internal_features" "-Crpath" "-Cdebuginfo=0" "-Lnative=X:\\repos\\rust\\build\\x86_64-pc-windows-msvc\\native\\rust-test-helpers" "-Clinker=lld" "-L" "X:\\repos\\rust\\build\\x86_64-pc-windows-msvc\\test\\ui\\asan-odr-win\\asan_odr_windows\\auxiliary" "-Zsanitizer=address"
stdout: none
--- stderr -------------------------------
error: linking with `lld` failed: exit code: 1
|
= note: "lld" "-flavor" "link" "/NOLOGO" "C:\\Users\\ADMINI~1\\AppData\\Local\\Temp\\rustcEwtKzP\\symbols.o" "/WHOLEARCHIVE:X:\\repos\\rust\\build\\x86_64-pc-windows-msvc\\stage1\\lib\\rustlib\\x86_64-pc-windows-msvc\\lib\\librustc-dev_rt.asan.a" "<1 object files omitted>" "X:\\repos\\rust\\build\\x86_64-pc-windows-msvc\\test\\ui\\asan-odr-win\\asan_odr_windows\\auxiliary/{libothercrate.rlib}" "X:\\repos\\rust\\build\\x86_64-pc-windows-msvc\\stage1\\lib\\rustlib\\x86_64-pc-windows-msvc\\lib\\std-972c03a8627cad3b.dll.lib" "X:\\repos\\rust\\build\\x86_64-pc-windows-msvc\\stage1\\lib\\rustlib\\x86_64-pc-windows-msvc\\lib/{libcompiler_builtins-5ad709b9972a6089.rlib}" "kernel32.lib" "kernel32.lib" "advapi32.lib" "ntdll.lib" "userenv.lib" "ws2_32.lib" "dbghelp.lib" "/defaultlib:msvcrt" "C:\\Users\\ADMINI~1\\AppData\\Local\\Temp\\rustcEwtKzP\\api-ms-win-core-synch-l1-2-0.dll_imports_indirect.lib" "C:\\Users\\ADMINI~1\\AppData\\Local\\Temp\\rustcEwtKzP\\bcryptprimitives.dll_imports_indirect.lib" "/NXCOMPAT" "/LIBPATH:X:\\repos\\rust\\build\\x86_64-pc-windows-msvc\\native\\rust-test-helpers" "/LIBPATH:X:\\repos\\rust\\build\\x86_64-pc-windows-msvc\\test\\ui\\asan-odr-win\\asan_odr_windows\\auxiliary" "/OUT:X:\\repos\\rust\\build\\x86_64-pc-windows-msvc\\test\\ui\\asan-odr-win\\asan_odr_windows\\a.exe" "/OPT:REF,ICF" "/DEBUG" "/PDBALTPATH:%_PDB%"
= note: some arguments are omitted. use `--verbose` to show all linker arguments
= note: lld: error: could not open 'X:\repos\rust\build\x86_64-pc-windows-msvc\stage1\lib\rustlib\x86_64-pc-windows-msvc\lib\librustc-dev_rt.asan.a': no such file or directory␍
error: aborting due to 1 previous error
------------------------------------------
failures:
[ui] tests\ui\asan-odr-win\asan_odr_windows.rs
```
</details>
Full `config.toml`:
<details>
<summary>Full `config.toml`</summary>
```
profile = "compiler"
change-id = 999999
[llvm]
#assertions = true
download-ci-llvm = true
[build]
build = "x86_64-pc-windows-msvc"
#profiler = true
[rust]
use-lld = true
lld = true
download-rustc = false
codegen-backends = ["llvm"]
deny-warnings = true
debug = false
debuginfo-level = 1
debug-logging = true
debug-assertions = true
debug-assertions-std = true
```
</details> | A-linkage,A-testsuite,T-compiler,O-windows-msvc,T-bootstrap,A-sanitizers,C-bug | low | Critical |
2,765,591,128 | yt-dlp | [youtube] `formats` extractor-arg: do not include `dashy` when only `duplicate` is passed | ### DO NOT REMOVE OR SKIP THE ISSUE TEMPLATE
- [X] I understand that I will be **blocked** if I *intentionally* remove or skip any mandatory\* field
### Checklist
- [X] I'm requesting a site-specific feature
- [X] I've verified that I have **updated yt-dlp to nightly or master** ([update instructions](https://github.com/yt-dlp/yt-dlp#update-channels))
- [X] I've checked that all provided URLs are playable in a browser with the same IP and same login details
- [X] I've searched [known issues](https://github.com/yt-dlp/yt-dlp/issues/3766) and the [bugtracker](https://github.com/yt-dlp/yt-dlp/issues?q=) for similar issues **including closed ones**. DO NOT post duplicates
- [X] I've read the [guidelines for opening an issue](https://github.com/yt-dlp/yt-dlp/blob/master/CONTRIBUTING.md#opening-an-issue)
- [X] I've read about [sharing account credentials](https://github.com/yt-dlp/yt-dlp/blob/master/CONTRIBUTING.md#are-you-willing-to-share-account-details-if-needed) and I'm willing to share it if required
### Region
_No response_
### Example URLs
https://youtube.com/watch?v=3KPY-gjmHWA
### Provide a description that is worded well enough to be understood
it should look like this --extractor-args "youtube:formats=-duplicate or --extractor-args "youtube:formats=-dashy
### Provide verbose output that clearly demonstrates the problem
- [X] Run **your** yt-dlp command with **-vU** flag added (`yt-dlp -vU <your command line>`)
- [ ] If using API, add `'verbose': True` to `YoutubeDL` params instead
- [X] Copy the WHOLE output (starting with `[debug] Command-line config`) and insert it below
### Complete Verbose Output
```shell
[debug] Command-line config: ['https://youtube.com/watch?v=3KPY-gjmHWA']
[debug] User config "/data/data/com.termux/files/home/.config/yt-dlp/config": ['--paths', 'storage/shared/Youtube', '--no-mtime', '-o', '%(title).120B %(id).30B %(uploader).29B %(availability)s %(upload_date>%d/%m/%Y)s.%(ext)s', '-S', '+hasaud', '--concurrent-fragments', '10', '--retries', '20', '--fragment-retries', '5', '--throttled-rate', '15625', '--sponsorblock-api', 'https://sponsor.ajay.app', '--trim-filenames', '184', '--write-thumbnail', '--convert-thumbnails', 'jpg', '--write-description', '--extractor-args', 'youtube:player_client=-ios,mweb,default,web,tv,web_safari,web_embedded,-android,-android_vr;lang=en;po_token=mweb+MlteR1Cpx1gQYl5_W5x110GDdunjLpeEs0f-tlj_S11CVAicFrEHibsr4ileHxQq2MZ89zAXaHWzaVkAGNR0IFgKarRoc7oWaG_YYuC3r06UPPrdlnDNT9T-mHK6,web+MlteR1Cpx1gQYl5_W5x110GDdunjLpeEs0f-tlj_S11CVAicFrEHibsr4ileHxQq2MZ89zAXaHWzaVkAGNR0IFgKarRoc7oWaG_YYuC3r06UPPrdlnDNT9T-mHK6,web_creator+MlteR1Cpx1gQYl5_W5x110GDdunjLpeEs0f-tlj_S11CVAicFrEHibsr4ileHxQq2MZ89zAXaHWzaVkAGNR0IFgKarRoc7oWaG_YYuC3r06UPPrdlnDNT9T-mHK6,tv+MlteR1Cpx1gQYl5_W5x110GDdunjLpeEs0f-tlj_S11CVAicFrEHibsr4ileHxQq2MZ89zAXaHWzaVkAGNR0IFgKarRoc7oWaG_YYuC3r06UPPrdlnDNT9T-mHK6,web_safari+MlteR1Cpx1gQYl5_W5x110GDdunjLpeEs0f-tlj_S11CVAicFrEHibsr4ileHxQq2MZ89zAXaHWzaVkAGNR0IFgKarRoc7oWaG_YYuC3r06UPPrdlnDNT9T-mHK6,web_embedded+MlteR1Cpx1gQYl5_W5x110GDdunjLpeEs0f-tlj_S11CVAicFrEHibsr4ileHxQq2MZ89zAXaHWzaVkAGNR0IFgKarRoc7oWaG_YYuC3r06UPPrdlnDNT9T-mHK6,android+MnTLGUKvYQChfcshpyfGKWPbaFbpllwe3Oua5Y2GCBATeQLE47g7VDHmhO0MBf_esPqKJ7Jyll6xG-Z-Kswxz-fYc60ZP5JIxidQe5vP8u_2XzslUFfxfZjb0iAAtIhJIPWud5yeECtrBQt0gPROJtJURmvw7A==,android_vr+MnTLGUKvYQChfcshpyfGKWPbaFbpllwe3Oua5Y2GCBATeQLE47g7VDHmhO0MBf_esPqKJ7Jyll6xG-Z-Kswxz-fYc60ZP5JIxidQe5vP8u_2XzslUFfxfZjb0iAAtIhJIPWud5yeECtrBQt0gPROJtJURmvw7A==;formats=duplicate;skip=translated_subs;comment_sort=top;max_comments=7000,all,7000,500', '--skip-download', '--print-to-file', '%(formats_table)+#l', '%(title).120B %(id).30B %(uploader).29B %(availability)s %(upload_date>%d/%m/%Y)s 3.txt', 'https://youtube.com/watch?v=3KPY-gjmHWA', '-v', '--sponsorblock-mark', 'all', '--embed-chapters', '--merge-output-format', 'mkv', '--audio-multistreams', '--video-multistreams', '--write-subs', '--write-auto-subs', '--sub-langs', 'en,en-US,vi,.*orig', '--no-download-archive', '--no-overwrites', '--continue', '--no-abort-on-error', '--print', 'urls', '--print-to-file', '%(urls)+#l', '--mark-watched', '--no-quiet', '--replace-in-metadata', 'title', ' ?#[^ ]+', '', '--buffer-size', '8192', '--no-hls-use-mpegts', '--write-info-json', '--write-playlist-metafiles', '--fixup', 'never', '--add-metadata', '--remux-video', 'mkv']
~ $ yt-dlp https://youtube.com/watch?v=3KPY-gjmHWA
[debug] Command-line config: ['https://youtube.com/watch?v=3KPY-gjmHWA']
[debug] User config "/data/data/com.termux/files/home/.config/yt-dlp/config": ['--paths', 'storage/shared/Youtube', '--no-mtime', '-o', '%(title).120B %(id).30B %(uploader).29B %(availability)s %(upload_date>%d/%m/%Y)s.%(ext)s', '-S', '+hasaud', '--concurrent-fragments', '10', '--retries', '20', '--fragment-retries', '5', '--throttled-rate', '15625', '--sponsorblock-api', 'https://sponsor.ajay.app', '--trim-filenames', '184', '--write-thumbnail', '--convert-thumbnails', 'jpg', '--write-description', '--extractor-args', 'youtube:player_client=-ios,mweb,default,web,tv,web_safari,web_embedded,-android,-android_vr;lang=en;po_token=mweb+MlteR1Cpx1gQYl5_W5x110GDdunjLpeEs0f-tlj_S11CVAicFrEHibsr4ileHxQq2MZ89zAXaHWzaVkAGNR0IFgKarRoc7oWaG_YYuC3r06UPPrdlnDNT9T-mHK6,web+MlteR1Cpx1gQYl5_W5x110GDdunjLpeEs0f-tlj_S11CVAicFrEHibsr4ileHxQq2MZ89zAXaHWzaVkAGNR0IFgKarRoc7oWaG_YYuC3r06UPPrdlnDNT9T-mHK6,web_creator+MlteR1Cpx1gQYl5_W5x110GDdunjLpeEs0f-tlj_S11CVAicFrEHibsr4ileHxQq2MZ89zAXaHWzaVkAGNR0IFgKarRoc7oWaG_YYuC3r06UPPrdlnDNT9T-mHK6,tv+MlteR1Cpx1gQYl5_W5x110GDdunjLpeEs0f-tlj_S11CVAicFrEHibsr4ileHxQq2MZ89zAXaHWzaVkAGNR0IFgKarRoc7oWaG_YYuC3r06UPPrdlnDNT9T-mHK6,web_safari+MlteR1Cpx1gQYl5_W5x110GDdunjLpeEs0f-tlj_S11CVAicFrEHibsr4ileHxQq2MZ89zAXaHWzaVkAGNR0IFgKarRoc7oWaG_YYuC3r06UPPrdlnDNT9T-mHK6,web_embedded+MlteR1Cpx1gQYl5_W5x110GDdunjLpeEs0f-tlj_S11CVAicFrEHibsr4ileHxQq2MZ89zAXaHWzaVkAGNR0IFgKarRoc7oWaG_YYuC3r06UPPrdlnDNT9T-mHK6,android+MnTLGUKvYQChfcshpyfGKWPbaFbpllwe3Oua5Y2GCBATeQLE47g7VDHmhO0MBf_esPqKJ7Jyll6xG-Z-Kswxz-fYc60ZP5JIxidQe5vP8u_2XzslUFfxfZjb0iAAtIhJIPWud5yeECtrBQt0gPROJtJURmvw7A==,android_vr+MnTLGUKvYQChfcshpyfGKWPbaFbpllwe3Oua5Y2GCBATeQLE47g7VDHmhO0MBf_esPqKJ7Jyll6xG-Z-Kswxz-fYc60ZP5JIxidQe5vP8u_2XzslUFfxfZjb0iAAtIhJIPWud5yeECtrBQt0gPROJtJURmvw7A==;formats=duplicate;skip=translated_subs;comment_sort=top;max_comments=7000,all,7000,500', '--skip-download', '--print-to-file', '%(formats_table)+#l', '%(title).120B %(id).30B %(uploader).29B %(availability)s %(upload_date>%d/%m/%Y)s 3.txt', 'https://youtube.com/watch?v=3KPY-gjmHWA', '-v', '--sponsorblock-mark', 'all', '--embed-chapters', '--merge-output-format', 'mkv', '--audio-multistreams', '--video-multistreams', '--write-subs', '--write-auto-subs', '--sub-langs', 'en,en-US,vi,.*orig', '--no-download-archive', '--no-overwrites', '--continue', '--no-abort-on-error', '--print', 'urls', '--print-to-file', '%(urls)+#l', '%(title).170B %(id).70B %(uploader)s %(availability)s %(upload_date>%d/%m/%Y)s.txt', '--mark-watched', '--no-quiet', '--replace-in-metadata', 'title', ' ?#[^ ]+', '', '--buffer-size', '8192', '--no-hls-use-mpegts', '--write-info-json', '--write-playlist-metafiles', '--fixup', 'never', '--add-metadata', '--remux-video', 'mkv']
[debug] Encodings: locale utf-8, fs utf-8, pref utf-8, out utf-8, error utf-8, screen utf-8
[debug] yt-dlp version [email protected] from yt-dlp/yt-dlp-nightly-builds [0b6b7742c] (pip)
[debug] Python 3.12.8 (CPython aarch64 64bit) - Linux-4.4.248-hadesKernel-v2.0-greatlte-aarch64-with-libc (OpenSSL 3.3.2 3 Sep 2024, libc)
[debug] exe versions: ffmpeg 7.1 (setts), ffprobe 7.1
[debug] Optional libraries: Cryptodome-3.21.0, brotli-1.1.0, certifi-2024.12.14, mutagen-1.47.0, requests-2.32.3, sqlite3-3.47.2, urllib3-2.3.0, websockets-14.1
[debug] Proxy map: {}
[debug] Request Handlers: urllib, requests, websockets
[debug] Loaded 1837 extractors
[youtube] Extracting URL: https://youtube.com/watch?v=3KPY-gjmHWA
[youtube] 3KPY-gjmHWA: Downloading webpage
[youtube] 3KPY-gjmHWA: Downloading mweb player API JSON
[youtube] 3KPY-gjmHWA: Downloading tv player API JSON
[youtube] 3KPY-gjmHWA: Downloading web safari player API JSON
[youtube] 3KPY-gjmHWA: Downloading web embedded client config
[youtube] 3KPY-gjmHWA: Downloading player 03dbdfab
[youtube] 3KPY-gjmHWA: Downloading web embedded player API JSON
[debug] Loading youtube-nsig.03dbdfab from cache
[debug] [youtube] Decrypted nsig 8Z7pqqTOr01aHgkha => 4acm4DmrDNLvhA
[debug] Loading youtube-nsig.03dbdfab from cache
[debug] [youtube] Decrypted nsig G5TRjTs6qGyDLNDPl => 8lyvfjh4P7wzPw
[debug] Loading youtube-nsig.03dbdfab from cache
[debug] [youtube] Decrypted nsig TTU2kPdeAr6MWKOEW => J6Ljwq0dYQQgiQ
[debug] Loading youtube-nsig.03dbdfab from cache
[debug] [youtube] Decrypted nsig exBGCID2wP0jXGp2s => aim0U0nmz8-0PA
[debug] Loading youtube-nsig.03dbdfab from cache
[debug] [youtube] Decrypted nsig YlCsfRk3zKFVwfiIe => 07Q7Nk3XROZEDw
[debug] Loading youtube-nsig.03dbdfab from cache
[debug] [youtube] Decrypted nsig wsZ4wkTTkcrvmxTl1 => AS0SN0a8A_8l8Q
[debug] Loading youtube-nsig.03dbdfab from cache
[debug] [youtube] Decrypted nsig GZ7ShiLJOAPH8--Vy => yqyMPzkQTuVFgw
[debug] Loading youtube-nsig.03dbdfab from cache
[debug] [youtube] Decrypted nsig j2ioDDk8x9Ob2gsnv => MwrngstiCiPWmA
[debug] Loading youtube-nsig.03dbdfab from cache
[debug] [youtube] Decrypted nsig JxdtGRI4k0bb8YBbe => MYBvl9YzaYo2hw
[debug] Loading youtube-nsig.03dbdfab from cache
[debug] [youtube] Decrypted nsig mCcdNb-u4AMPSDaMu => iAuDTf-mhmyJ_w
[youtube] 3KPY-gjmHWA: Downloading m3u8 information
[info] 3KPY-gjmHWA: Downloading subtitles: en, vi, en-orig
[debug] Sort order given by user: +hasaud
[debug] Sort order given by extractor: quality, res, fps, hdr:12, source, vcodec, channels, acodec, lang, proto
[debug] Formats sorted by: hasvid, ie_pref, +hasaud, quality, res, fps, hdr:12(7), source, vcodec, channels, acodec, lang, proto, size, br, asr, vext, aext, id
[debug] Replacing all ' ?#[^ ]+' in title with ''
[MetadataParser] Did not find ' ?#[^ ]+' in title
[SponsorBlock] Fetching SponsorBlock segments
[debug] SponsorBlock query: https://sponsor.ajay.app/api/skipSegments/62cd?service=YouTube&categories=%5B%22poi_highlight%22%2C+%22interaction%22%2C+%22intro%22%2C+%22filler%22%2C+%22chapter%22%2C+%22outro%22%2C+%22music_offtopic%22%2C+%22selfpromo%22%2C+%22sponsor%22%2C+%22preview%22%5D&actionTypes=%5B%22skip%22%2C+%22poi%22%2C+%22chapter%22%5D
[SponsorBlock] Found 8 segments in the SponsorBlock database
[debug] Default format spec: bestvideo+bestaudio/best
[info] 3KPY-gjmHWA: Downloading 1 format(s): 401-4+251-4
https://rr1---sn-8pxuo5hvcpax-nboe.googlevideo.com/videoplayback?expire=1735826004&ei=9EV2Z6jwJ9y02roPjZuH0Qc&ip=103.129.191.95&id=o-AMT2cNcDbTodF4o1dR1LXl1hmRi3EKGhjw6x_gExpIyH&itag=401&aitags=133%2C134%2C135%2C136%2C137%2C160%2C242%2C243%2C244%2C247%2C248%2C271%2C278%2C313%2C394%2C395%2C396%2C397%2C398%2C399%2C400%2C401&source=youtube&requiressl=yes&xpc=EgVo2aDSNQ%3D%3D&met=1735804404%2C&mh=ma&mm=31%2C29&mn=sn-8pxuo5hvcpax-nboe%2Csn-42u-nbozl&ms=au%2Crdu&mv=m&mvi=1&pl=24&rms=au%2Cau&initcwndbps=323750&bui=AfMhrI_GQy8c-jAEe1shhU9yFnYHEbBKcbpBcxph4WSjZpLJcad99FzEeAoY4W_y9JfP0gIecnwZvskG&spc=x-caUGvzz7qm2T7IM04ESOa-lNbylOgURZ750IRZOfuq_Z-8jVj8LTYdEMzm&vprv=1&svpuc=1&mime=video%2Fmp4&ns=3BKN70R4CIFbyPw1hYlqIsYQ&rqh=1&gir=yes&clen=509375628&dur=706.299&lmt=1734002473926689&mt=1735803894&fvip=6&keepalive=yes&fexp=51326932%2C51335594%2C51371294&c=WEB_EMBEDDED_PLAYER&sefc=1&txp=4532434&n=iAuDTf-mhmyJ_w&sparams=expire%2Cei%2Cip%2Cid%2Caitags%2Csource%2Crequiressl%2Cxpc%2Cbui%2Cspc%2Cvprv%2Csvpuc%2Cmime%2Cns%2Crqh%2Cgir%2Cclen%2Cdur%2Clmt&sig=AJfQdSswRAIgFM5hVUl409y2PkKwR2uGW9aMx54-DM-S2oNrkSrp-8UCIEicvuzbseWRoKKj0p5B_uaqVC097Q6T9hrF50ZAFKjc&lsparams=met%2Cmh%2Cmm%2Cmn%2Cms%2Cmv%2Cmvi%2Cpl%2Crms%2Cinitcwndbps&lsig=AGluJ3MwRQIhAMxsZ7CU3F3AFW-pPQST7RczqSl8K4ggQ9vHdhOlyzLNAiBEII4nZlBzfKgTROD1Ll4uUAGjDNwOXr0KcwxjWgZ0vA%3D%3D&pot=MlteR1Cpx1gQYl5_W5x110GDdunjLpeEs0f-tlj_S11CVAicFrEHibsr4ileHxQq2MZ89zAXaHWzaVkAGNR0IFgKarRoc7oWaG_YYuC3r06UPPrdlnDNT9T-mHK6
https://rr1---sn-8pxuo5hvcpax-nboe.googlevideo.com/videoplayback?expire=1735826004&ei=9EV2Z6jwJ9y02roPjZuH0Qc&ip=103.129.191.95&id=o-AMT2cNcDbTodF4o1dR1LXl1hmRi3EKGhjw6x_gExpIyH&itag=251&source=youtube&requiressl=yes&xpc=EgVo2aDSNQ%3D%3D&met=1735804404%2C&mh=ma&mm=31%2C29&mn=sn-8pxuo5hvcpax-nboe%2Csn-42u-nbozl&ms=au%2Crdu&mv=m&mvi=1&pl=24&rms=au%2Cau&initcwndbps=323750&bui=AfMhrI_GQy8c-jAEe1shhU9yFnYHEbBKcbpBcxph4WSjZpLJcad99FzEeAoY4W_y9JfP0gIecnwZvskG&spc=x-caUGvzz7qm2T7IM04ESOa-lNbylOgURZ750IRZOfuq_Z-8jVj8LTYdEMzm&vprv=1&svpuc=1&mime=audio%2Fwebm&ns=3BKN70R4CIFbyPw1hYlqIsYQ&rqh=1&gir=yes&clen=11502264&dur=706.321&lmt=1728958109615809&mt=1735803894&fvip=6&keepalive=yes&fexp=51326932%2C51335594%2C51371294&c=WEB_EMBEDDED_PLAYER&sefc=1&txp=4532434&n=iAuDTf-mhmyJ_w&sparams=expire%2Cei%2Cip%2Cid%2Citag%2Csource%2Crequiressl%2Cxpc%2Cbui%2Cspc%2Cvprv%2Csvpuc%2Cmime%2Cns%2Crqh%2Cgir%2Cclen%2Cdur%2Clmt&sig=AJfQdSswRQIgCLttscdELxiFoM1lE77_IVwZBZHKB_LodeXayXaoHUoCIQC1ByViy6B0M0Dg3JYUrplur99N9Sy8obtWTcDygpajMg%3D%3D&lsparams=met%2Cmh%2Cmm%2Cmn%2Cms%2Cmv%2Cmvi%2Cpl%2Crms%2Cinitcwndbps&lsig=AGluJ3MwRQIhAMxsZ7CU3F3AFW-pPQST7RczqSl8K4ggQ9vHdhOlyzLNAiBEII4nZlBzfKgTROD1Ll4uUAGjDNwOXr0KcwxjWgZ0vA%3D%3D&pot=MlteR1Cpx1gQYl5_W5x110GDdunjLpeEs0f-tlj_S11CVAicFrEHibsr4ileHxQq2MZ89zAXaHWzaVkAGNR0IFgKarRoc7oWaG_YYuC3r06UPPrdlnDNT9T-mHK6
[info] Writing '%(formats_table)+#l' to: storage/shared/Youtube/Do NOT buy the Freedom Phone!! 🤬 3KPY-gjmHWA Mrwhosetheboss public 24⧸07⧸2021 3.txt
[info] Writing '%(urls)+#l' to: storage/shared/Youtube/Do NOT buy the Freedom Phone!! 🤬 3KPY-gjmHWA Mrwhosetheboss public 24⧸07⧸2021.txt
[youtube] Extracting URL: https://youtube.com/watch?v=3KPY-gjmHWA
[youtube] 3KPY-gjmHWA: Downloading webpage
[youtube] 3KPY-gjmHWA: Downloading mweb player API JSON
[youtube] 3KPY-gjmHWA: Downloading tv player API JSON
[youtube] 3KPY-gjmHWA: Downloading web safari player API JSON
[youtube] 3KPY-gjmHWA: Downloading web embedded client config
[youtube] 3KPY-gjmHWA: Downloading web embedded player API JSON
[debug] Loading youtube-nsig.03dbdfab from cache
[debug] [youtube] Decrypted nsig TmD8R2YpJGKM8jcYO => HxLQXhWy0DW-uw
[debug] Loading youtube-nsig.03dbdfab from cache
[debug] [youtube] Decrypted nsig B1m8OeVmDA-XcIJ56 => leh7yApWu_JJKQ
[debug] Loading youtube-nsig.03dbdfab from cache
[debug] [youtube] Decrypted nsig jAXA0HxgDIrwaxxQh => 2UrGo0uMMHllZg
[debug] Loading youtube-nsig.03dbdfab from cache
[debug] [youtube] Decrypted nsig YOyYvLrgqMqVuXPl9 => tgQ9EBHOHElRIA
[debug] Loading youtube-nsig.03dbdfab from cache
[debug] [youtube] Decrypted nsig uv5lLQAttpHaQq2ks => gz-HXLyHECxMjg
[debug] Loading youtube-nsig.03dbdfab from cache
[debug] [youtube] Decrypted nsig MGE6zVYTOjZV79Cuv => NUEKd-qK42WvFQ
[debug] Loading youtube-nsig.03dbdfab from cache
[debug] [youtube] Decrypted nsig u74HMfR_DvxniZdxT => 3_-l5G9dxTOH6w
[debug] Loading youtube-nsig.03dbdfab from cache
[debug] [youtube] Decrypted nsig _BBCKmf7_iFG9Lfpy => jKfLV0FIhQr6oQ
[debug] Loading youtube-nsig.03dbdfab from cache
[debug] [youtube] Decrypted nsig Y2H1tupM-GXCoi2sP => _mQBpzJ6CiI-pQ
[debug] Loading youtube-nsig.03dbdfab from cache
[debug] [youtube] Decrypted nsig iDZKfK0Ra6DdJ7ULH => Kwq1zCc8_EmCgQ
[youtube] 3KPY-gjmHWA: Downloading m3u8 information
[info] 3KPY-gjmHWA: Downloading subtitles: en, vi, en-orig
[debug] Sort order given by user: +hasaud
[debug] Sort order given by extractor: quality, res, fps, hdr:12, source, vcodec, channels, acodec, lang, proto
[debug] Formats sorted by: hasvid, ie_pref, +hasaud, quality, res, fps, hdr:12(7), source, vcodec, channels, acodec, lang, proto, size, br, asr, vext, aext, id
[debug] Replacing all ' ?#[^ ]+' in title with ''
[MetadataParser] Did not find ' ?#[^ ]+' in title
[SponsorBlock] Fetching SponsorBlock segments
[debug] SponsorBlock query: https://sponsor.ajay.app/api/skipSegments/62cd?service=YouTube&categories=%5B%22poi_highlight%22%2C+%22interaction%22%2C+%22intro%22%2C+%22filler%22%2C+%22chapter%22%2C+%22outro%22%2C+%22music_offtopic%22%2C+%22selfpromo%22%2C+%22sponsor%22%2C+%22preview%22%5D&actionTypes=%5B%22skip%22%2C+%22poi%22%2C+%22chapter%22%5D
[SponsorBlock] Found 8 segments in the SponsorBlock database
[debug] Default format spec: bestvideo+bestaudio/best
[info] 3KPY-gjmHWA: Downloading 1 format(s): 401-4+251-4
https://rr1---sn-8pxuo5hvcpax-nboe.googlevideo.com/videoplayback?expire=1735826042&ei=GkZ2Z6ryF92D2roPp9a9qAE&ip=103.129.191.95&id=o-AFiaAxaKuQK7E0iFAVMM-9FtcGfapFcoUGAIZ0xlEO2h&itag=401&aitags=133%2C134%2C135%2C136%2C137%2C160%2C242%2C243%2C244%2C247%2C248%2C271%2C278%2C313%2C394%2C395%2C396%2C397%2C398%2C399%2C400%2C401&source=youtube&requiressl=yes&xpc=EgVo2aDSNQ%3D%3D&met=1735804442%2C&mh=ma&mm=31%2C29&mn=sn-8pxuo5hvcpax-nboe%2Csn-42u-nbozl&ms=au%2Crdu&mv=m&mvi=1&pl=24&rms=au%2Cau&initcwndbps=323750&bui=AfMhrI9brnGe1NJCBwPaCq68Gjqyrzc9Td7LdQ8nvXhzK4QMdCUMcuRUbbZX8iV1gYDxopTrKd4mUKpr&spc=x-caUBG2nLXD9EHDXlXJhhPi65Ql60ImvD9KVxaHU83qcY8aPmcVy6eHasxz&vprv=1&svpuc=1&mime=video%2Fmp4&ns=etPNMIvE7J2V4dfDQnTGPxoQ&rqh=1&gir=yes&clen=509375628&dur=706.299&lmt=1734002473926689&mt=1735803894&fvip=6&keepalive=yes&fexp=51326932%2C51335594%2C51371294&c=WEB_EMBEDDED_PLAYER&sefc=1&txp=4532434&n=Kwq1zCc8_EmCgQ&sparams=expire%2Cei%2Cip%2Cid%2Caitags%2Csource%2Crequiressl%2Cxpc%2Cbui%2Cspc%2Cvprv%2Csvpuc%2Cmime%2Cns%2Crqh%2Cgir%2Cclen%2Cdur%2Clmt&sig=AJfQdSswRQIgLF1w4uH_d1FiXio8uDgMlra-TidaV8km6AsLyzZfVugCIQCN6MbPbPSkbe8P9MYPLdUzbxfRvgxR4BpA82oOpntuhQ%3D%3D&lsparams=met%2Cmh%2Cmm%2Cmn%2Cms%2Cmv%2Cmvi%2Cpl%2Crms%2Cinitcwndbps&lsig=AGluJ3MwRAIgdlQYDkMwRHVVzFAPWKjTOtLP_Y4OQW1-8FgYJYDyArcCIBY1aLu_NvLctG_9B_6Ajc-khpGPqfmaZxR3rl_k5zJf&pot=MlteR1Cpx1gQYl5_W5x110GDdunjLpeEs0f-tlj_S11CVAicFrEHibsr4ileHxQq2MZ89zAXaHWzaVkAGNR0IFgKarRoc7oWaG_YYuC3r06UPPrdlnDNT9T-mHK6
https://rr1---sn-8pxuo5hvcpax-nboe.googlevideo.com/videoplayback?expire=1735826042&ei=GkZ2Z6ryF92D2roPp9a9qAE&ip=103.129.191.95&id=o-AFiaAxaKuQK7E0iFAVMM-9FtcGfapFcoUGAIZ0xlEO2h&itag=251&source=youtube&requiressl=yes&xpc=EgVo2aDSNQ%3D%3D&met=1735804442%2C&mh=ma&mm=31%2C29&mn=sn-8pxuo5hvcpax-nboe%2Csn-42u-nbozl&ms=au%2Crdu&mv=m&mvi=1&pl=24&rms=au%2Cau&initcwndbps=323750&bui=AfMhrI9brnGe1NJCBwPaCq68Gjqyrzc9Td7LdQ8nvXhzK4QMdCUMcuRUbbZX8iV1gYDxopTrKd4mUKpr&spc=x-caUBG2nLXD9EHDXlXJhhPi65Ql60ImvD9KVxaHU83qcY8aPmcVy6eHasxz&vprv=1&svpuc=1&mime=audio%2Fwebm&ns=etPNMIvE7J2V4dfDQnTGPxoQ&rqh=1&gir=yes&clen=11502264&dur=706.321&lmt=1728958109615809&mt=1735803894&fvip=6&keepalive=yes&fexp=51326932%2C51335594%2C51371294&c=WEB_EMBEDDED_PLAYER&sefc=1&txp=4532434&n=Kwq1zCc8_EmCgQ&sparams=expire%2Cei%2Cip%2Cid%2Citag%2Csource%2Crequiressl%2Cxpc%2Cbui%2Cspc%2Cvprv%2Csvpuc%2Cmime%2Cns%2Crqh%2Cgir%2Cclen%2Cdur%2Clmt&sig=AJfQdSswRQIgYR8GIvuK6jRWWmfKswNd4d3SN_QVhAFtApApCngHQEUCIQCbETAsn7IbLnB2qYfaihB8eEAscHPxxzROaJCeX1QbMw%3D%3D&lsparams=met%2Cmh%2Cmm%2Cmn%2Cms%2Cmv%2Cmvi%2Cpl%2Crms%2Cinitcwndbps&lsig=AGluJ3MwRAIgdlQYDkMwRHVVzFAPWKjTOtLP_Y4OQW1-8FgYJYDyArcCIBY1aLu_NvLctG_9B_6Ajc-khpGPqfmaZxR3rl_k5zJf&pot=MlteR1Cpx1gQYl5_W5x110GDdunjLpeEs0f-tlj_S11CVAicFrEHibsr4ileHxQq2MZ89zAXaHWzaVkAGNR0IFgKarRoc7oWaG_YYuC3r06UPPrdlnDNT9T-mHK6
[info] Writing '%(formats_table)+#l' to: storage/shared/Youtube/Do NOT buy the Freedom Phone!! 🤬 3KPY-gjmHWA Mrwhosetheboss public 24⧸07⧸2021 3.txt
[info] Writing '%(urls)+#l' to: storage/shared/Youtube/Do NOT buy the Freedom Phone!! 🤬 3KPY-gjmHWA Mrwhosetheboss public 24⧸07⧸2021.txt
```
| site-enhancement,site:youtube | low | Critical |
2,765,606,610 | react-native | measureInWindow returns the same when scrolling in iOS | ### Description
```javascript
import React, { useState, useRef } from 'react';
import { View, ScrollView, Text, StyleSheet } from 'react-native';
const App = () => {
const viewRef = useRef(null);
const [viewPosition, setViewPosition] = useState({ x: 0, y: 0 });
let timer = null
const onScroll = () => {
console.log('onScroll')
if (viewRef && viewRef.current) {
try {
viewRef.current.measureInWindow(function (x, y, width, height) {
console.log({x, y, width, height})
setViewPosition({ x: x, y: y });
});
} catch (error) {
console.error('Error measuring the view:', error);
}
}
};
return (
<ScrollView onScroll={onScroll}>
<View style={styles.container}>
<Text style={styles.text}>Scroll the screen</Text>
<View ref={viewRef} style={styles.measuredView}>
<Text style={styles.text}>This is the view to be measured x:{viewPosition.x} y:{viewPosition.y} </Text>
</View>
<View style={styles.bottom}></View>
</View>
</ScrollView>
);
};
const styles = StyleSheet.create({
bottom: {
height: 700,
width: 100,
backgroundColor: 'red'
},
container: {
flex: 1,
alignItems: 'center',
justifyContent: 'center',
},
text: {
fontSize: 20,
margin: 20,
},
measuredView: {
width: 200,
height: 200,
backgroundColor: 'lightblue',
margin: 20,
},
});
export default App;
```
When scoll the ScrollView, the the viewRef's position not change. It occurs only in iOS。Android works good.
### Steps to reproduce
1. npx @react-native-community/cli@latest init AwesomeProject --version 0.76.3
2. use the code above to replace the App.tsx
3. run in ios simulator
4. scroll the ScrollView
### React Native Version
0.76.3
### Affected Platforms
Runtime - iOS
### Areas
Fabric - The New Renderer
### Output of `npx react-native info`
```text
System:
OS: macOS 14.5
CPU: (12) arm64 Apple M3 Pro
Memory: 82.00 MB / 18.00 GB
Shell:
version: "5.9"
path: /bin/zsh
Binaries:
Node:
version: 20.11.0
path: ~/.nvm/versions/node/v20.11.0/bin/node
Yarn: Not Found
npm:
version: 10.2.4
path: ~/.nvm/versions/node/v20.11.0/bin/npm
Watchman: Not Found
Managers:
CocoaPods: Not Found
SDKs:
iOS SDK:
Platforms:
- DriverKit 23.5
- iOS 17.5
- macOS 14.5
- tvOS 17.5
- visionOS 1.2
- watchOS 10.5
Android SDK:
API Levels:
- "34"
- "35"
Build Tools:
- 34.0.0
- 35.0.0
System Images:
- android-34 | Google APIs ARM 64 v8a
- android-34 | Google Play ARM 64 v8a
- android-35 | Google Play ARM 64 v8a
Android NDK: Not Found
IDEs:
Android Studio: 2024.1 AI-241.18034.62.2412.12266719
Xcode:
version: 15.4/15F31d
path: /usr/bin/xcodebuild
Languages:
Java:
version: 17.0.12
path: /usr/bin/javac
Ruby:
version: 3.1.0
path: /Users/didi/.rvm/rubies/ruby-3.1.0/bin/ruby
npmPackages:
"@react-native-community/cli":
installed: 15.0.1
wanted: 15.0.1
react:
installed: 18.3.1
wanted: 18.3.1
react-native:
installed: 0.76.3
wanted: 0.76.3
react-native-macos: Not Found
npmGlobalPackages:
"*react-native*": Not Found
Android:
hermesEnabled: true
newArchEnabled: true
iOS:
hermesEnabled: Not found
newArchEnabled: false
```
### Stacktrace or Logs
```text
no crash.
```
### Reproducer
https://github.com/thuman/awesomedemo
### Screenshots and Videos
_No response_ | Platform: iOS,Issue: Author Provided Repro,Needs: Repro,Newer Patch Available,Needs: Attention,Type: New Architecture | low | Critical |
2,765,624,055 | opencv | CUDA function is combined with opencv for onnx inference | ### Describe the doc issue
I encountered problems when I tried to combine cuda programming with ONNX inference. After image processing with CUDA function, I obtained CUDA data of uchar*. Instead of GPU-->CPU-->GPU operations, I wanted to use opencv to directly reason my data, but I had no idea. Is there a simple demo?
this is my code:
{
Mat src = imread(ImagePath);
int row = src.rows;
int col = src.cols;
uchar* src_cuda = ToGpu(src,col,row);
Mat show_dst(640,640,CV_8UC3);
uchar* dst_cuda = Resize(src_cuda,row,col,640,640); // GPU Resze
}
I want to read yolov8n.onnx for inference
### Fix suggestion
_No response_ | category: documentation | low | Minor |
2,765,631,970 | pytorch | redundant recompilation caused by duplicated Sym() | ### 🐛 Describe the bug
Hello
I've been trying to reduce the number of recompiles during Megatron training recently and noticed that strange recompiles happenned on RMSNorm.
```
@torch.compile(dynamic=True)
def rmsnorm_without_weight(hidden_states, eps=1e-6, dtype=torch.bfloat16):
variance = hidden_states.to(torch.float32).pow(2).mean(-1, keepdim=True)
hidden_states = hidden_states * torch.rsqrt(variance + eps)
hidden_states = hidden_states.to(dtype)
return hidden_states
```
I compared the two compilation results from tlparse, and found that the only difference between the two kernels was the duplicated "Sym()" of arg0_1:
```
# kernel 1:
def forward(self, arg0_1: "Sym(s0)", arg1_1: "Sym(s1)", arg2_1: "bf16[s0, 1, s1][s1, s1, 1]cuda:0"):
# kernel 2:
def forward(self, arg0_1: "Sym(s2)", arg1_1: "Sym(s1)", arg2_1: "bf16[s0, 1, s1][s1, s1, 1]cuda:0"):
```
And this caused the guard failure:
```
L['hidden_states'].size()[0]*L['hidden_states'].size()[2] < 2147483648 # kernel 1
L['hidden_states'].size()[2]*L['hidden_states'].size()[0] < 2147483648 # kernel 2
```
I don't understand under what circumstances such a strange aliasing phenomenon would occur. And I want to figure out how to prevent recompiles like this.
### Error logs
tlparse output of Kernel 1
[2_0_0.zip](https://github.com/user-attachments/files/18288896/2_0_0.zip)
tlparse output of Kernel 2
[2_4_0.zip](https://github.com/user-attachments/files/18288898/2_4_0.zip)
### Versions
PyTorch version: 2.5.1
Is debug build: False
CUDA used to build PyTorch: 12.6
ROCM used to build PyTorch: N/A
OS: Ubuntu 20.04.6 LTS (x86_64)
GCC version: (Ubuntu 9.4.0-1ubuntu1~20.04.2) 9.4.0
Clang version: Could not collect
CMake version: version 3.29.1
Libc version: glibc-2.31
Python version: 3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0] (64-bit runtime)
Python platform: Linux-5.14.0-3.0.3.kwai.x86_64-x86_64-with-glibc2.31
Is CUDA available: True
CUDA runtime version: 12.6.77
CUDA_MODULE_LOADING set to: LAZY
GPU models and configuration:
GPU 0: NVIDIA H800
GPU 1: NVIDIA H800
GPU 2: NVIDIA H800
GPU 3: NVIDIA H800
GPU 4: NVIDIA H800
GPU 5: NVIDIA H800
GPU 6: NVIDIA H800
GPU 7: NVIDIA H800
Nvidia driver version: 535.129.03
cuDNN version: Probably one of the following:
/usr/lib/x86_64-linux-gnu/libcudnn.so.9.5.0
/usr/lib/x86_64-linux-gnu/libcudnn_adv.so.9.5.0
/usr/lib/x86_64-linux-gnu/libcudnn_cnn.so.9.5.0
/usr/lib/x86_64-linux-gnu/libcudnn_engines_precompiled.so.9.5.0
/usr/lib/x86_64-linux-gnu/libcudnn_engines_runtime_compiled.so.9.5.0
/usr/lib/x86_64-linux-gnu/libcudnn_graph.so.9.5.0
/usr/lib/x86_64-linux-gnu/libcudnn_heuristic.so.9.5.0
/usr/lib/x86_64-linux-gnu/libcudnn_ops.so.9.5.0
HIP runtime version: N/A
MIOpen runtime version: N/A
Is XNNPACK available: True
CPU:
Architecture: x86_64
CPU op-mode(s): 32-bit, 64-bit
Byte Order: Little Endian
Address sizes: 52 bits physical, 57 bits virtual
CPU(s): 192
On-line CPU(s) list: 0-191
Thread(s) per core: 2
Core(s) per socket: 48
Socket(s): 2
NUMA node(s): 2
Vendor ID: GenuineIntel
CPU family: 6
Model: 143
Model name: Intel(R) Xeon(R) Platinum 8468
Stepping: 8
CPU MHz: 2100.000
CPU max MHz: 3800.0000
CPU min MHz: 800.0000
BogoMIPS: 4200.00
Virtualization: VT-x
L1d cache: 4.5 MiB
L1i cache: 3 MiB
L2 cache: 192 MiB
L3 cache: 210 MiB
NUMA node0 CPU(s): 0-47,96-143
NUMA node1 CPU(s): 48-95,144-191
Vulnerability Itlb multihit: Not affected
Vulnerability L1tf: Not affected
Vulnerability Mds: Not affected
Vulnerability Meltdown: Not affected
Vulnerability Mmio stale data: Not affected
Vulnerability Retbleed: Not affected
Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl
Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization
Vulnerability Spectre v2: Mitigation; Enhanced IBRS, IBPB conditional, RSB filling, PBRSB-eIBRS SW sequence
Vulnerability Srbds: Not affected
Vulnerability Tsx async abort: Not affected
Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf tsc_known_freq pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb cat_l3 cat_l2 cdp_l3 invpcid_single intel_ppin cdp_l2 ssbd mba ibrs ibpb stibp ibrs_enhanced tpr_shadow vnmi flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb intel_pt avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local split_lock_detect avx_vnni avx512_bf16 wbnoinvd dtherm ida arat pln pts hwp hwp_act_window hwp_epp hwp_pkg_req avx512vbmi umip pku ospke waitpkg avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg tme avx512_vpopcntdq la57 rdpid bus_lock_detect cldemote movdiri movdir64b enqcmd fsrm md_clear serialize tsxldtrk pconfig arch_lbr amx_bf16 avx512_fp16 amx_tile amx_int8 flush_l1d arch_capabilities
Versions of relevant libraries:
[pip3] numpy==1.26.4
[pip3] nvidia-cudnn-frontend==1.6.1
[pip3] nvtx==0.2.10
[pip3] pytorch-lightning==1.9.5
[pip3] torch==2.5.1
[pip3] torch-tb-profiler==0.4.3
[pip3] torchcde==0.2.5
[pip3] torchcfm==1.0.5
[pip3] torchdiffeq==0.2.4
[pip3] torchdyn==1.0.6
[pip3] torchmetrics==1.5.1
[pip3] torchsde==0.2.6
[pip3] torchvision==0.17.2+c1d70fe
[pip3] triton==3.1.0
[conda] Could not collect
cc @chauhang @penguinwu @ezyang @bobrenjc93 @voznesenskym @EikanWang @jgong5 @Guobing-Chen @XiaobingSuper @zhuhaozhe @blzheng @wenzhe-nrv @jiayisunx @chenyang78 @kadeng @amjames | triaged,oncall: pt2,module: dynamic shapes,module: dynamo | low | Critical |
2,765,632,914 | pytorch | [AMD] [ROCm] Numerical difference between Pytorch 2.6.0.dev of ROCm 6.2 and ROCm 6.3 | ### 🐛 Describe the bug
# Description
I am getting different numerical output results between Pytorch 2.6.0.dev of ROCm 6.2 and ROCm 6.3.
All the tests in the https://github.com/linkedin/Liger-Kernel/pull/506 pass with PyTorch 2.6.0.dev of ROCm 6.2
However, one of the tests fail in the environment with PyTorch 2.6.0.dev of ROCm 6.3.
- Only one failed test in ROCm 6.3
- FAILED CONVERGENCE TEST
```
====================================================== short test summary info =======================================================
FAILED test/convergence/test_mini_models.py::test_mini_model[mini_mllama-32-0.0001-dtype2-1e-08-1e-05-0.005-1e-05-0.005-1e-05] - AssertionError: Number of mismatched elements: 2
Mismatch at index (0, 7): tensor1[(0, 7)] = 3.0651497840881348, tensor2[(0, 7)] = 3.0652356147766113
Mismatch at index (0, 9): tensor1[(0, 9)] = 1.470238447189331, tensor2[(0, 9)] = 1.4702625274658203
======================================== 1 failed, 16 passed, 2 warnings in 94.82s (0:01:34) ==================
```
# Steps to reproduce:
1. Launch docker container
```
#!/bin/bash
sudo docker run -it \
--network=host \
--group-add=video \
--ipc=host \
--cap-add=SYS_PTRACE \
--security-opt seccomp=unconfined \
--device /dev/kfd \
--device /dev/dri \
-v <path-to-Liger-Kernel>:/liger-kernel-workspace \
rocm/pytorch:rocm6.3_ubuntu22.04_py3.10_pytorch_release_2.5.0_preview \
/bin/bash
```
2. Setup
```
python -m pip uninstall -y torch torchvision triton
python -m pip install -e .[dev] --extra-index-url https://download.pytorch.org/whl/nightly/rocm6.3
python -m pip install triton==3.1.0
```
3. Run tests
``` make test-convergence ```
https://github.com/linkedin/Liger-Kernel/pull/506
### Versions
```bash
root@root:/liger-kernel-workspace# python collect_env.py /opt/conda/envs/py_3.10/lib/python3.10/site-packages/torch/utils/_pytree.py:185: FutureWarning: optree is installed but the version is too ol
d to support PyTorch Dynamo in C++ pytree. C++ pytree support is disabled. Please consider upgrading optree using `python3 -m pip install --u
pgrade 'optree>=0.13.0'`.
warnings.warn(
Collecting environment information...
PyTorch version: 2.6.0.dev20241231+rocm6.3
Is debug build: False
CUDA used to build PyTorch: N/A
ROCM used to build PyTorch: 6.3.42131-fa1d09cbd
OS: Ubuntu 22.04.5 LTS (x86_64)
GCC version: (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0
Clang version: 18.0.0git (https://github.com/RadeonOpenCompute/llvm-project roc-6.3.1 24463 5d263cec09eef95b1ed5f3e7f6a578c616efa0a4)
CMake version: version 3.26.4
Libc version: glibc-2.35
Python version: 3.10.15 (main, Oct 3 2024, 07:27:34) [GCC 11.2.0] (64-bit runtime)
Python platform: Linux-5.15.0-84-generic-x86_64-with-glibc2.35
Is CUDA available: True
CUDA runtime version: Could not collect
CUDA_MODULE_LOADING set to: LAZY
GPU models and configuration: AMD Instinct MI210 (gfx90a:sramecc+:xnack-)
Nvidia driver version: Could not collect
cuDNN version: Could not collect
HIP runtime version: 6.3.42131
MIOpen runtime version: 3.3.0
Is XNNPACK available: True
CPU:
Architecture: x86_64
CPU op-mode(s): 32-bit, 64-bit
Address sizes: 48 bits physical, 48 bits virtual
Byte Order: Little Endian
CPU(s): 32
On-line CPU(s) list: 0-31
Vendor ID: AuthenticAMD
Model name: AMD Ryzen 9 7950X 16-Core Processor
CPU family: 25
Model: 97
Thread(s) per core: 2
Core(s) per socket: 16
Socket(s): 1
Stepping: 2
Frequency boost: enabled
CPU max MHz: 5879.8818
CPU min MHz: 3000.0000
BogoMIPS: 8983.59
Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx mmxext fxsr_opt pdpe1gb rdtscp lm constant_tsc rep_good nopl nonstop_tsc cpuid extd_apicid aperfmperf rapl pni pclmulqdq monitor ssse3 fma cx16 sse4_1 sse4_2 x2apic movbe popcnt aes xsave avx f16c rdrand lahf_lm cmp_legacy svm extapic cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw ibs skinit wdt tce topoext perfctr_core perfctr_nb bpext perfctr_llc mwaitx cpb cat_l3 cdp_l3 hw_pstate ssbd mba ibrs ibpb stibp vmmcall fsgsbase bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local avx512_bf16 clzero irperf xsaveerptr rdpru wbnoinvd cppc arat npt lbrv svm_lock nrip_save tsc_scale vmcb_clean flushbyasid decodeassists pausefilter pfthreshold avic v_vmsave_vmload vgif v_spec_ctrl avx512vbmi umip pku ospke avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg avx512_vpopcntdq rdpid overflow_recov succor smca fsrm flush_l1d
Virtualization: AMD-V
L1d cache: 512 KiB (16 instances)
L1i cache: 512 KiB (16 instances)
L2 cache: 16 MiB (16 instances)
L3 cache: 64 MiB (2 instances)
NUMA node(s): 1
NUMA node0 CPU(s): 0-31
Vulnerability Gather data sampling: Not affected
Vulnerability Itlb multihit: Not affected
Vulnerability L1tf: Not affected
Vulnerability Mds: Not affected
Vulnerability Meltdown: Not affected
Vulnerability Mmio stale data: Not affected
Vulnerability Retbleed: Not affected
Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl and seccomp
Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization
Vulnerability Spectre v2: Mitigation; Retpolines, IBPB conditional, IBRS_FW, STIBP always-on, RSB filling, PBRSB-eIBRS Not affected
Vulnerability Srbds: Not affected
Vulnerability Tsx async abort: Not affected
Versions of relevant libraries:
[pip3] flake8==7.1.1
[pip3] mypy==1.10.0
[pip3] mypy-extensions==1.0.0
[pip3] numpy==1.26.4
[pip3] onnx==1.16.1
[pip3] onnxscript==0.1.0.dev20240817
[pip3] optree==0.12.1
[pip3] pytorch-triton-rocm==3.2.0+git0d4682f0
[pip3] torch==2.6.0.dev20241231+rocm6.3
[pip3] triton==3.1.0
[conda] No relevant packages
```
cc @ezyang @gchanan @zou3519 @kadeng @msaroufim @jeffdaily @sunway513 @jithunnair-amd @pruthvistony @ROCmSupport @dllehr-amd @jataylo @hongxiayang @naromero77amd | high priority,module: rocm,triaged | low | Critical |
2,765,648,669 | TypeScript | Compiler option to switch lib .d.ts `any`s to `unknown` | ### 🔍 Search Terms
compiler option flag lib.d.ts noImplicitAny unknown any
### ✅ Viability Checklist
- [x] This wouldn't be a breaking change in existing TypeScript/JavaScript code
- [x] This wouldn't change the runtime behavior of existing JavaScript code
- [x] This could be implemented without emitting different JS based on the types of the expressions
- [x] This isn't a runtime feature (e.g. library functionality, non-ECMAScript syntax with JavaScript output, new syntax sugar for JS, etc.)
- [x] This isn't a request to add a new utility type: https://github.com/microsoft/TypeScript/wiki/No-New-Utility-Types
- [x] This feature would agree with the rest of our Design Goals: https://github.com/Microsoft/TypeScript/wiki/TypeScript-Design-Goals
### ⭐ Suggestion
A few built-in (`lib*.d.ts`) types include `any`, even though `unknown` would be safer. Most notably:
* [`JSON.parse()`](https://developer.mozilla.org/en-US/docs/Web/JavaScript/Reference/Global_Objects/JSON/parse): https://github.com/microsoft/TypeScript/blob/56a08250f3516b3f5bc120d6c7ab4450a9a69352/src/lib/es5.d.ts#L1144
* [`.json()`](https://developer.mozilla.org/en-US/docs/Web/API/Response/json): https://github.com/microsoft/TypeScript/blob/56a08250f3516b3f5bc120d6c7ab4450a9a69352/src/lib/dom.generated.d.ts#L19416
* [`Storage`](https://developer.mozilla.org/en-US/docs/Web/API/Web_Storage_API/Using_the_Web_Storage_API#basic_concepts): https://github.com/microsoft/TypeScript/blob/56a08250f3516b3f5bc120d6c7ab4450a9a69352/src/lib/dom.generated.d.ts#L22262
These are kept as `any` for legacy support reasons: it would be a massive breaking change to restrict them to `unknown`. But, for newer projects and those that don't rely on those `any`s, switching them to `unknown` would be much safer long-term.
Proposal: could we have a compiler option to switch the lib definition `any`s to `unknown`s? Maybe, `strictLibDefinitions`? `useUnknownInLibDefinitions`? _(I'm not convinced of those specific names)_
### 📃 Motivating Example
Using this compiler option will prevent many of the common `any`s from sneaking into projects that use built-ins such as `JSON.parse` and `Response`.
For example, this code does not have a type error by default, but would with the new compiler option enabled:
```ts
const data = JSON.parse(`"clearly-a-string"`);
// ^? any (today)
// ^? unknown (with this compiler option)
console.log(data.some.property.that.does.not.exist);
```
### 💻 Use Cases
I'm not sure that this could even be enabled with `strict` anytime soon. It might introduce a lot of type errors in even many projects that are already in strict mode but happen to use `JSON.parse` et al.
This is not the same as #27265. That issue tracks a flag to handle implicit `any`s differently. This is for a flag to change the definitions in TypeScript's built-in `.d.ts` files.
I don't _think_ this is the same as https://github.com/microsoft/TypeScript/issues/26188. Per https://github.com/microsoft/TypeScript/issues/60899#issuecomment-2567457149: I'd interpreted that one as suggesting making the change always - with varying levels of compiler-option-orientation in the comments.
The implementation details of this might be tricky. The dom lib generator could theoretically produce two `.d.ts` outputs for each of today's files: one with `any` and one with `unknown`. Or, if two files aren't doable, there could be an intrinsic declared that switches between `any` and `unknown`. | Suggestion,Needs Proposal | low | Critical |
2,765,649,409 | pytorch | torch-nightly doesn't support tesla v100 | ### 🐛 Describe the bug
env:TeslaV100,driver 560.35.03 cuda 12.4
use pip3 install --pre torch torchvision torchaudio --index-url https://download.pytorch.org/whl/nightly/cu124
python:
import torch
print(torch.randn(5, 5).to(device)+torch.randn(5, 5).to(device))
but cuda12.4 supports v100,i can't find which torch version supports v100+cuda12.4 or other gpu
<img width="569" alt="1·33" src="https://github.com/user-attachments/assets/b7b0c42d-65ee-412a-aabf-cc1f2fc502c2" />
### Versions
2.6.0
cc @seemethere @malfet @osalpekar @atalman @ptrblck @msaroufim @eqy @ezyang @gchanan @zou3519 @kadeng | needs reproduction,module: binaries,module: cuda,triaged | low | Critical |
2,765,672,368 | pytorch | Compile error for custom op with optional mutable tensor list argument | ### 🐛 Describe the bug
It showed that the Torch auto functionalization doesn't support custom op with optional mutable tensor list argument.
The following code shows this problem. "Tensor(a!)[]? out_list" argument of the op is not supported for auto functionalization:
```
import torch
@torch.library.custom_op("mylib::mysin", mutates_args=["out_list"], schema="(Tensor x, Tensor(a!)[]? out_list) -> (Tensor)")
def mysin(x: torch.Tensor, out_list: list[torch.Tensor] = None) -> torch.Tensor:
r = x.sin()
return r
@torch.library.register_fake("mylib::mysin")
def mysin_fake(x, out_list: list[torch.Tensor] = None) -> torch.Tensor:
return torch.empty_like(x)
def fn(x):
x = x * 3
s = [torch.empty_like(x)]
x= mysin(x, out_list=s)
x = x / 3
return x
fn = torch.compile(fn)
x = torch.randn(3, requires_grad=False)
y= fn(x)
print(y)
```
When executing the above code, the following exception happens:
```
File "/home/haifchen/working/envs/env_test_nightly/lib/python3.10/site-packages/torch/_subclasses/functional_tensor.py", line 535, in __torch_dispatch__
outs_unwrapped = func._op_dk(
torch._dynamo.exc.BackendCompilerFailed: backend='inductor' raised:
RuntimeError: Found a custom (non-ATen) operator whose output has alias annotations: mylib::mysin(Tensor x, Tensor(a!)[]? out_list) -> Tensor. We only support functionalizing operators whose outputs do not have alias annotations (e.g. 'Tensor(a)' is a Tensor with an alias annotation whereas 'Tensor' is a Tensor without. The '(a)' is the alias annotation). The alias annotation specifies that the output Tensor shares storage with an input that has the same annotation. Please check if (1) the output needs to be an output (if not, don't return it), (2) if the output doesn't share storage with any inputs, then delete the alias annotation. (3) if the output indeed shares storage with an input, then add a .clone() before returning it to prevent storage sharing and then delete the alias annotation. Otherwise, please file an issue on GitHub.
While executing %x_1 : [num_users=1] = call_function[target=torch.ops.mylib.mysin.default](args = (%x,), kwargs = {out_list: [%empty_like]})
Original traceback:
File "/home/haifchen/working/test/test-custom-op-alias.py", line 136, in fn
x= mysin(x, out_list=s)
File "/home/haifchen/working/envs/env_test_nightly/lib/python3.10/site-packages/torch/_library/custom_ops.py", line 669, in __call__
return self._opoverload(*args, **kwargs)
```
If we change the custom op schema to "(Tensor x, Tensor(a!)[] out_list) -> (Tensor)", it works.
Is there any fundamental difficulties to support optional mutable tensor list argument?
### Versions
Collecting environment information...
PyTorch version: 2.6.0.dev20240914+cpu
Is debug build: False
CUDA used to build PyTorch: None
ROCM used to build PyTorch: N/A
OS: Ubuntu 22.04 LTS (x86_64)
GCC version: (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0
Clang version: 14.0.0-1ubuntu1.1
CMake version: version 3.22.1
Libc version: glibc-2.35
Python version: 3.10.12 (main, Sep 11 2024, 15:47:36) [GCC 11.4.0] (64-bit runtime)
Python platform: Linux-5.15.0-122-generic-x86_64-with-glibc2.35
Is CUDA available: False
CUDA runtime version: No CUDA
CUDA_MODULE_LOADING set to: N/A
GPU models and configuration: No CUDA
Nvidia driver version: No CUDA
cuDNN version: No CUDA
HIP runtime version: N/A
MIOpen runtime version: N/A
Is XNNPACK available: True
CPU:
Architecture: x86_64
CPU op-mode(s): 32-bit, 64-bit
Address sizes: 43 bits physical, 48 bits virtual
Byte Order: Little Endian
CPU(s): 12
On-line CPU(s) list: 0-11
Vendor ID: GenuineIntel
Model name: Intel(R) Xeon(R) Gold 6230 CPU @ 2.10GHz
CPU family: 6
Model: 85
Thread(s) per core: 1
Core(s) per socket: 6
Socket(s): 2
Stepping: 0
BogoMIPS: 4190.15
Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ss ht syscall nx pdpe1gb rdtscp lm constant_tsc arch_perfmon nopl xtopology tsc_reliable nonstop_tsc cpuid tsc_known_freq pni pclmulqdq vmx ssse3 fma cx16 pcid sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand hypervisor lahf_lm abm 3dnowprefetch invpcid_single pti ssbd ibrs ibpb stibp tpr_shadow vnmi ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 invpcid avx512f avx512dq rdseed adx smap clflushopt clwb avx512cd avx512bw avx512vl xsaveopt xsavec xsaves arat pku ospke md_clear flush_l1d arch_capabilities
Virtualization: VT-x
Hypervisor vendor: VMware
Virtualization type: full
L1d cache: 384 KiB (12 instances)
L1i cache: 384 KiB (12 instances)
L2 cache: 12 MiB (12 instances)
L3 cache: 55 MiB (2 instances)
NUMA node(s): 1
NUMA node0 CPU(s): 0-11
Vulnerability Gather data sampling: Unknown: Dependent on hypervisor status
Vulnerability Itlb multihit: KVM: Mitigation: VMX disabled
Vulnerability L1tf: Mitigation; PTE Inversion; VMX flush not necessary, SMT disabled
Vulnerability Mds: Mitigation; Clear CPU buffers; SMT Host state unknown
Vulnerability Meltdown: Mitigation; PTI
Vulnerability Mmio stale data: Mitigation; Clear CPU buffers; SMT Host state unknown
Vulnerability Reg file data sampling: Not affected
Vulnerability Retbleed: Mitigation; IBRS
Vulnerability Spec rstack overflow: Not affected
Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl and seccomp
Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization
Vulnerability Spectre v2: Mitigation; IBRS; IBPB conditional; STIBP disabled; RSB filling; PBRSB-eIBRS Not affected; BHI SW loop, KVM SW loop
Vulnerability Srbds: Not affected
Vulnerability Tsx async abort: Not affected
Versions of relevant libraries:
[pip3] numpy==2.1.1
[pip3] torch==2.6.0.dev20240914+cpu
[conda] Could not collect
cc @bdhirsh @ezyang @chauhang @penguinwu @zou3519 @yf225 | triaged,module: custom-operators,module: functionalization,oncall: pt2,module: aotdispatch,module: pt2-dispatcher | low | Critical |
2,765,677,608 | svelte | Using clsx incorporating class declaration with tailwind-merge causes error | ### Describe the bug
Combining the latest clsx supporting `HTMLAttributes` with tailwind-merge creates type incompatibility.
**HTMLAttributes declared by svelte**
```
export interface HTMLAttributes<T extends EventTarget> extends AriaAttributes, DOMAttributes<T> {
class?: string | import('clsx').ClassArray | import('clsx').ClassDictionary | undefined | null;
...
}
```
**Expected type from tailwind-merge**
```export type ClassNameValue = ClassNameArray | string | 0 | 0n | false | undefined | null```
### Error Logs
```shell
Argument of type 'string | ClassArray | ClassDictionary | null | undefined' is not assignable to parameter of type 'ClassNameValue'.
Type 'ClassArray' is not assignable to type 'ClassNameValue'.
Type 'ClassValue[]' is not assignable to type 'ClassNameArray'.
Type 'ClassValue' is not assignable to type 'ClassNameValue'.
Type 'number' is not assignable to type 'ClassNameValue'. (ts)
: 'size-12',
cssClass,
)}
```
### Reproduction
```
<script lang="ts">
import { twMerge } from 'tailwind-merge'
import type { HTMLButtonAttributes } from 'svelte/elements'
import type { Snippet } from 'svelte'
interface Props extends HTMLButtonAttributes {
children?: Snippet
}
let { class: cssClass, children, ...rest }: Props = $props()
</script>
<button {...rest} class={twMerge('rounded', cssClass)}>
{@render children?.()}
</button>
```
### System Info
```shell
npmPackages:
svelte: ^5.16.0
tailwind-merge: ^2.6.0
```
### Severity
blocking an upgrade
### Hacky workaround
One possibility is to redefine the `class` property as a common type (eg a simple `string`).
```
interface Props extends HTMLButtonAttributes {
children?: Snippet
class?: string
}
``` | types / typescript | low | Critical |
2,765,681,888 | rust | Placing an attribute on a generic argument confuses the parser | ### Code
```Rust
struct Foo<T>(T);
fn main() {
let foo: Foo<#[cfg(not(wrong))] String> = todo!();
}
```
### Current output
```Shell
error: invalid const generic expression
--> /playground/src/main.rs:8:37
|
8 | let foo: Foo<#[cfg(not(wrong))] String> = todo!();
| ^^^^^^
|
help: expressions must be enclosed in braces to be used as const generic arguments
|
8 | let foo: Foo<#[cfg(not(wrong))] { String }> = todo!();
```
### Desired output
```Shell
error: attributes are not allowed on generic arguments
--> /playground/src/main.rs:8:37
|
8 | let foo: Foo<#[cfg(not(wrong))] String> = todo!();
| ^^^^^^^^^^^^^^^^^^
| attribute not allowed in this context
help: remove the attribute to allow the code to compile:
8 | let foo: Foo<String> = todo!();
```
### Rationale and extra context
Playground link: https://play.rust-lang.org/?version=nightly&mode=debug&edition=2021&gist=eaf1097ff4efa3734d3a5e3faa3cb10f
### Other cases
```Rust
If one applies the suggestion made in the current error, you get the "same" error message suggesting to add another level of brackets.
```
### Rust Version
```Shell
Build using the Nightly version: 1.85.0-nightly
(2025-01-01 45d11e51bb66c2deb63a)
```
### Anything else?
_No response_ | A-diagnostics,A-parser,T-compiler | low | Critical |
2,765,710,236 | godot | Godot4.4dev7: Still spams loading messages | ### Tested versions
v4.4.dev7.mono.official [46c8f8c5c]
### System information
Windows11, Ubuntu
### Issue description
I have already reported this problem to https://github.com/godotengine/godot/issues/99535. and https://github.com/godotengine/godot/pull/99667
And according to the Godot4.4dev7 release notes it should be fixed, but loading messages are still being generated unnecessarily.
https://godotengine.github.io/godot-interactive-changelog/#4.4-dev7
## Initial loaded the project looks good
```
Godot Engine v4.4.dev7.mono.official (c) 2007-present Juan Linietsky, Ariel Manzur & Godot Contributors.
Loading resource: C:/Users/mikes/AppData/Local/Godot/editor_doc_cache-4.4.res
--- Debug adapter server started on port 6006 ---
--- GDScript language server started on port 6005 ---
Loaded system CA certificates
Loading resource: res://test/ResourceLoadTest.tscn
Loading resource: res://test/resource_load_test.gd
```
## Run the test scene, you can see using 'load' spams the messages
```
Running: D:/development/Godot_v4.4-dev7_mono_win64/Godot_v4.4-dev7_mono_win64.exe
%s --path
%s D:/development/workspace/issues/verbose_reload_messages
%s --remote-debug
%s tcp://127.0.0.1:6007
%s --editor-pid
%s 17892
%s --position
%s 2624,372
%s res://test/ResourceLoadTest.tscn
Generated 'res://test/ResourceLoadTest.tscn' preview in 9566 usec
Godot Engine v4.4.dev7.mono.official.46c8f8c5c - https://godotengine.org
TextServer: Added interface "Dummy"
TextServer: Added interface "ICU / HarfBuzz / Graphite (Built-in)"
Devices:
#0: NVIDIA NVIDIA GeForce RTX 4070 Ti - Supported, Discrete
Optional extension VK_EXT_astc_decode_mode not found
Optional extension VK_EXT_debug_marker not found
- Vulkan Variable Rate Shading supported:
Pipeline fragment shading rate
Primitive fragment shading rate
Attachment fragment shading rate, min texel size: (16, 16), max texel size: (16, 16), max fragment size: (4, 4)
- Vulkan multiview supported:
max view count: 32
max instances: 134217727
- Vulkan subgroup:
size: 32
min size: 32
max size: 32
stages: STAGE_VERTEX, STAGE_TESSELLATION_CONTROL, STAGE_TESSELLATION_EVALUATION, STAGE_GEOMETRY, STAGE_FRAGMENT, STAGE_COMPUTE, STAGE_RAYGEN_KHR, STAGE_ANY_HIT_KHR, STAGE_CLOSEST_HIT_KHR, STAGE_MISS_KHR, STAGE_INTERSECTION_KHR, STAGE_CALLABLE_KHR, STAGE_TASK_NV, STAGE_MESH_NV
supported ops: FEATURE_BASIC, FEATURE_VOTE, FEATURE_ARITHMETIC, FEATURE_BALLOT, FEATURE_SHUFFLE, FEATURE_SHUFFLE_RELATIVE, FEATURE_CLUSTERED, FEATURE_QUAD, FEATURE_PARTITIONED_NV
quad operations in all stages
Vulkan 1.3.289 - Forward+ - Using Device #0: NVIDIA - NVIDIA GeForce RTX 4070 Ti
Startup PSO cache (3.1 MiB)
Using "winink" pen tablet driver...
Creating VMA small objects pool for memory type index 1
Shader 'CanvasSdfShaderRD' (group 0) SHA256: 77e45c1369b65f0b1756b806d9083ba7ea67c39eba4c61c8658234e08087ab99
Shader 'SkeletonShaderRD' (group 0) SHA256: 87a41572ba7d291323acf772c9d484c833bfae57743206ebaa69f753f0545d5a
Shader 'SortShaderRD' (group 0) SHA256: 471f5da1ee4a6b21b56b35a0a6a0c7b2fd2209f54ac37665ef4f60749dc03356
Shader 'ParticlesShaderRD' (group 0) SHA256: 5d52df901ee444a19f0ccc4541f8ba8dc2d32b5e681e8dc02f2f235448ec100a
Shader 'ParticlesCopyShaderRD' (group 0) SHA256: 2bba87c2af154e36421c5303527840e84b1f64c328b1c48001972ba199e5cb36
Shader 'CanvasShaderRD' (group 0) SHA256: f83d8068413a45cea6e2b5f546b7ba81ae9e042a37e56866e10dcc51b81661d7
Shader 'CanvasOcclusionShaderRD' (group 0) SHA256: 474a127c1342c166158ee6e498e73bdccb349f06c7e54e2552a4f05f02e66f09
Shader 'ClusterRenderShaderRD' (group 0) SHA256: 10486f3b6e58b4dd6351c8a22163a0959da681181f3d91f9b35b21c18af7bbad
Shader 'ClusterStoreShaderRD' (group 0) SHA256: ba2c6bb6486d0065d10feda088721b1ff49a7455afea50c160d59a5e730bd632
Shader 'ClusterDebugShaderRD' (group 0) SHA256: 0fc3a4145fb0593b7979ef24e96686868f96991310c620653f5a5c10d6a8bd58
Shader 'SceneForwardClusteredShaderRD' (group 0) SHA256: 1bb11d7a68ceae2e4dcb410d31f63d2d6e82d7e7a77fe2b04591cb9fd30184ee
Shader 'SceneForwardClusteredShaderRD' (group 1) SHA256: f5398f5ee40ec9181e6b7a32f1fb76bfcdf58fe6bc342df8891c0be2dc431c2e
Shader 'SceneForwardClusteredShaderRD' (group 2) SHA256: 4ca2d5609dc74e4e4c336da247e22619f80c877a2f61b1dfc9cffe6d8f17c8b4
Shader 'SceneForwardClusteredShaderRD' (group 3) SHA256: 1ccb74095cf52d34013a88568b9a8ad7527e0a288446a0c152549f3bf8b8518e
Shader 'BestFitNormalShaderRD' (group 0) SHA256: 8ffb22cb537ee4bfd09822c4623c161b33abec186400688d957654c43b13bad5
Shader 'ResolveShaderRD' (group 0) SHA256: 4c97907291c0ed83c1c9eaa9ddb6d555eb75e67d586dcef0368e8df55eddc35b
Shader 'TaaResolveShaderRD' (group 0) SHA256: fa9b4c3566ab6d2b0727b54ff9b4289ae3e7c24d25fc7eadd2dc7c131119dc5a
Shader 'Fsr2DepthClipPassShaderRD' (group 0) SHA256: 6c10a12c0d4664f94cb70b55e4d6948f6040cd68a3c063b9b421c0f7e53204cd
Shader 'Fsr2ReconstructPreviousDepthPassShaderRD' (group 0) SHA256: 900e471f384febf63669ecb37c4d78dc514bf2173a97333d1a19cc51fc66a1e9
Shader 'Fsr2LockPassShaderRD' (group 0) SHA256: 5562de0986b602167f7e26a8a4e4bf2c371477729ce2ccfe8583672c58a2c813
Shader 'Fsr2AccumulatePassShaderRD' (group 0) SHA256: 045b9c553940ce1e6107eda0ae48c9afce3d0e2ac1663e32fe0888d7ab6526a7
Shader 'Fsr2RcasPassShaderRD' (group 0) SHA256: 891e22cd1d088ddeb9cdbfbce896d6948a0656462542c4d2b70ee85c69366419
Shader 'Fsr2ComputeLuminancePyramidPassShaderRD' (group 0) SHA256: 282792f9816f8833afe70dd7db442fed7b8c59c72bd4264670f29c2a08e1bfbd
Shader 'Fsr2AutogenReactivePassShaderRD' (group 0) SHA256: a75408a3af2db56d20e213dfbd4c91ede902ba861921d8f2262b8e1d30240a7c
Shader 'Fsr2TcrAutogenPassShaderRD' (group 0) SHA256: 846e5bbb1aa3971873d711b0bfb4c593b2aad02dcf3aa098e328786e9ba38c23
Shader 'SsEffectsDownsampleShaderRD' (group 0) SHA256: 5074a5a1bd50cbe5082d34cdc45cc61526a273c2dafde2214f004205c659da92
Shader 'SsilShaderRD' (group 0) SHA256: 0a88985faa4e43dd8c8b68812be9ef19eb851e2c5715107b4c32fcac16eba76d
Shader 'SsilImportanceMapShaderRD' (group 0) SHA256: 4b1bf2803bc67dba51ac662987cef6c51e8cc0cc48435b0fc75392f8bfab622b
Shader 'SsilBlurShaderRD' (group 0) SHA256: 424b9696d111595d6837a686c6d0f7f90eb5529d5b53739fd7d0d74b2756adc5
Shader 'SsilInterleaveShaderRD' (group 0) SHA256: bf9990758208c4453ad9d0919b0d016c5a8e349d249d0ba191beadca252d0571
Shader 'SsaoShaderRD' (group 0) SHA256: 6b55b1b4ecb762c287449423e3cfbb7e00eda47ac8698ee4c7002ae18aef3f2c
Shader 'SsaoImportanceMapShaderRD' (group 0) SHA256: dcf4410044aaaffada8757132c706b4a3465bfde49077d3e80f87de6442b1376
Shader 'SsaoBlurShaderRD' (group 0) SHA256: af82da4ed5d9bcfbcf01b6b2317dd537a9c0995f709f7cdafc8ebebb455c8fe0
Shader 'SsaoInterleaveShaderRD' (group 0) SHA256: ad5de6d3542ac078185a843939802a82f0a5b2e1cafb294397acf6ecf10af3aa
Shader 'ScreenSpaceReflectionScaleShaderRD' (group 0) SHA256: e6ee3f0b6bb7f7197d5122cd0caee7863de96e02450b6fd92aa837305fce7a82
Shader 'ScreenSpaceReflectionShaderRD' (group 0) SHA256: 90333cfa89267fa907fcdb4f7d2108a6d560f2bf1ce588c376111004d68b2f05
Shader 'ScreenSpaceReflectionFilterShaderRD' (group 0) SHA256: 8389baba6db0b301fd1c9f9fa1044cd91ce2412cce119e75c9f73398dbf577cd
Shader 'SubsurfaceScatteringShaderRD' (group 0) SHA256: 7e9c783f6cdee7982815c8e029846782471ba69582ed951b6a10397c019a249a
Shader 'SkyShaderRD' (group 0) SHA256: 06629b95fdf2956224d7ba4b404c10f27474d080dd7ab1b6bccf212c7bdc44fe
Shader 'VoxelGiShaderRD' (group 0) SHA256: 1ac508c0080394ecbab0cf258d9f1f121e978085163972e48cb9d59d10ac10b4
Shader 'VoxelGiDebugShaderRD' (group 0) SHA256: f94e88a3595bad778ba61976dcd95755a1038ef6dfbc7ba9e15d465a5514e359
Shader 'SdfgiPreprocessShaderRD' (group 0) SHA256: 65a90da4cdbb95286777fe99c404de14a8e4808fbe3dc30d70a652d19d3b4159
Shader 'SdfgiDirectLightShaderRD' (group 0) SHA256: 74f7612cee95e0401167a45d973f8e7c202730b425372335e5c3a044755ad4e9
Shader 'SdfgiIntegrateShaderRD' (group 0) SHA256: 6b7dc48ae7b5ee6aba6fa6d3db45f60227ad2494131848578e8fc8626ffdbabb
Shader 'GiShaderRD' (group 0) SHA256: 5748d22534478c009e298b06926b05c92a300abdd0d60ef4c4f6267c5d2f1024
Shader 'SdfgiDebugShaderRD' (group 0) SHA256: 245a7c3be81e911b2adf8c3504b14911a0f0fcdda4fcc98c117b142c77d0e09d
Shader 'SdfgiDebugProbesShaderRD' (group 0) SHA256: 5337782649472851ec89ce7e36adef31918efb798ebe15c0147beb7c25de1adb
Shader 'VolumetricFogShaderRD' (group 0) SHA256: b092d865b0ce712c1563615275521217e63bcf03b984721b7337e57a32fb45c9
Shader 'VolumetricFogProcessShaderRD' (group 0) SHA256: d7569be56ea49bd8e051e977e8a60ed9350e3b54283d319af94f40e46e4b6e28
Shader 'BokehDofShaderRD' (group 0) SHA256: cdc329fb15139dcae19937b183945c48dc854bb644ebb750fcf08352bf58c401
Shader 'CopyShaderRD' (group 0) SHA256: ba013ccec819557fed345c81ad8d4ade56f581da6144331650bb4846dcfe7a03
Shader 'CopyToFbShaderRD' (group 0) SHA256: d71dfa0b7ee1f00185d54ee3a6cf0b63f760936a978b3255f4dc949503a0517c
Shader 'CubeToDpShaderRD' (group 0) SHA256: c7eb2150013188f234926912e6a9fd3e7479429a13407a40fef8f24abd6d9746
Shader 'CubemapDownsamplerShaderRD' (group 0) SHA256: bd81c1c46cd619748a80769b66ac4bf7c9ede1f6c031cd92080d4777ae61651c
Shader 'CubemapFilterShaderRD' (group 0) SHA256: d1b866bd82bd6fae2ebb7201890678a540be3a3d2feb86c3050955e1aeeeda44
Shader 'CubemapRoughnessShaderRD' (group 0) SHA256: 444604ac2dd3bf42987510ab135cc42091874b1a3656135e9f007c79f4491508
Shader 'SpecularMergeShaderRD' (group 0) SHA256: a8f0862c3e2fc9beaa6e25804d6a7df97a34d1707d61cb0299450c5aabc9e33e
Shader 'ShadowFrustumShaderRD' (group 0) SHA256: 3c60a3230c9afa3578a50021cb101463dbc5e72a269932abc388788a3185f100
Shader 'MotionVectorsShaderRD' (group 0) SHA256: 231122bcd64c4c4f9fe7368348f3b7ed4e7501eba3bd6a692cf6b3484dcc685d
Shader 'LuminanceReduceShaderRD' (group 0) SHA256: 3a39696f235e5cda5d792537f6d86ad0f55e5590c7b9b30df2ef6173379bcee6
Shader 'TonemapShaderRD' (group 0) SHA256: 5b7ab09c8d3b094f00aa4928f7ccfa7430c6f1d2882d3b4e0751db63d52b6407
Shader 'VrsShaderRD' (group 0) SHA256: 118bb5474f8d4b94f69aebf800ddb63cd06ca0c1e381c113eb2b9c795cb67e40
Shader 'FsrUpscaleShaderRD' (group 0) SHA256: 67c7b37a79c73c32051d8282572f8bb517aea720bada457083761662b5ce7797
Shader 'BlitShaderRD' (group 0) SHA256: 60b72570245d5a464fb0c04ffcef0e642a15a222ee0de28d468f8a470fcde26c
WASAPI: Activated output_device using IAudioClient3 interface
WASAPI: wFormatTag = 65534
WASAPI: nChannels = 2
WASAPI: nSamplesPerSec = 48000
WASAPI: nAvgBytesPerSec = 384000
WASAPI: nBlockAlign = 8
WASAPI: wBitsPerSample = 32
WASAPI: cbSize = 22
WASAPI: mix_rate = 48000
WASAPI: fundamental_period_frames = 480
WASAPI: min_period_frames = 480
WASAPI: max_period_frames = 480
WASAPI: selected a period frame size of 480
WASAPI: detected 2 channels
WASAPI: audio buffer frames: 480 calculated latency: 10ms
TextServer: Primary interface set to: "ICU / HarfBuzz / Graphite (Built-in)".
.NET: Initializing module...
Found hostfxr: C:/Program Files/dotnet/host/fxr/8.0.7/hostfxr.dll
.NET: hostfxr initialized
.NET: GodotPlugins initialized
ERROR: .NET: Failed to load project assembly
CORE API HASH: 2852872746
EDITOR API HASH: 3988302787
Loaded system CA certificates
Loading resource: res://test/ResourceLoadTest.tscn
Loading resource: res://test/resource_load_test.gd
Run direct instanciate the script
Run lazy loading the script: cache mode reuse
Loading resource: res://test/example_script.gd
Loading resource: res://test/example_script.gd
Loading resource: res://test/example_script.gd
Loading resource: res://test/example_script.gd
Loading resource: res://test/example_script.gd
Loading resource: res://test/example_script.gd
Loading resource: res://test/example_script.gd
Loading resource: res://test/example_script.gd
Loading resource: res://test/example_script.gd
Loading resource: res://test/example_script.gd
Run direct load the script
Loading resource: res://test/example_script.gd
Loading resource: res://test/example_script.gd
Loading resource: res://test/example_script.gd
Loading resource: res://test/example_script.gd
Loading resource: res://test/example_script.gd
Loading resource: res://test/example_script.gd
Loading resource: res://test/example_script.gd
Loading resource: res://test/example_script.gd
Loading resource: res://test/example_script.gd
Loading resource: res://test/example_script.gd
--- Debugging process stopped ---
```
And i see this warning i the debug console when using the --verbose flag
```
W 0:00:00:0072 _debug_messenger_callback: GENERAL - Message Id Number: 0 | Message Id Name: Loader Message
windows_read_data_files_in_registry: Registry lookup failed to get layer manifest files.
Objects - 1
Object[0] - VK_OBJECT_TYPE_INSTANCE, Handle 1966503863936
<C++ Source> drivers/vulkan/rendering_context_driver_vulkan.cpp:639 @ _debug_messenger_callback()
```
### Steps to reproduce
Use the attached example project and run the scene.
```
Loading resource: res://test/ResourceLoadTest.tscn
Loading resource: res://test/resource_load_test.gd
Run direct instanciate the script
Run lazy loading the script: cache mode reuse
Loading resource: res://test/example_script.gd
Loading resource: res://test/example_script.gd
Loading resource: res://test/example_script.gd
Loading resource: res://test/example_script.gd
Loading resource: res://test/example_script.gd
Loading resource: res://test/example_script.gd
Loading resource: res://test/example_script.gd
Loading resource: res://test/example_script.gd
Loading resource: res://test/example_script.gd
Loading resource: res://test/example_script.gd
Run direct load the script
Loading resource: res://test/example_script.gd
Loading resource: res://test/example_script.gd
Loading resource: res://test/example_script.gd
Loading resource: res://test/example_script.gd
Loading resource: res://test/example_script.gd
Loading resource: res://test/example_script.gd
Loading resource: res://test/example_script.gd
Loading resource: res://test/example_script.gd
Loading resource: res://test/example_script.gd
Loading resource: res://test/example_script.gd
```
### Minimal reproduction project (MRP)
[verbose_reload_messages.zip](https://github.com/user-attachments/files/18289393/verbose_reload_messages.zip)
| bug,topic:core | low | Critical |
2,765,710,674 | vscode | {Linked:Bug9528434} The interactive control in the @workspace tooltip is not accessible using keyboard (Tab or Arrow) keys: A11y_VS Code_Copilot Chat_Keyboard | ### GitHub Tags:
#A11yMAS; #A11yTCS; #A11ySev2; #DesktopApp; #BM-VisualStudioCodeClient-Win32-Jan2024; #Visual Studio Code Client; #Win32; #Win11; #WCAG2.1.1; #FTP; #Keyboard; #ED:Bug9528434
### Environment and OS details:
Version: 1.97.0-insider (user setup)
Windows 11 Enterprise Version 24H2
OS Build: 26100.2605
### Repro Steps:
1. Open Visual Studio Code Insiders editor.
2. Tab till Copilot chat Window and press enter.
3. Navigate to Chat(Ctrl+Alt+I) in Left Nav and activate it.
4. Navigate to Ask copilot text field type /Help Command and press enter.
5. Navigate to @workspace Bulleted List.
6. Observed that the interactive control in the @workspace tooltip is not accessible using keyboard.
### Actual Result:
The interactive control in the @workspace tooltip is not accessible using keyboard (Tab or Arrow) keys.
### Expected Result:
The interactive control in the @workspace tooltip should be accessible with keyboard (Tab or Arrow) keys.
### User Impact:
Keyboard users will face difficulty if the interactive control in the @workspace tooltip is not accessible using keyboard.
### Attachment:
| bug,accessibility,chat | low | Critical |
2,765,726,545 | vscode | {Linked:Bug9577427} When a list item is selected in Pick Model, the list box closes and reopens without any user interaction: A11y_VS Code_Copilot Chat_Pick model_Usability | ### GitHub Tags:
#A11yUsable; #A11yTCS; #DesktopApp; #BM-VisualStudioCodeClient-Win32-Jan2024; #Visual Studio Code Client; #Win32; #Win11; #FTP; #ED:Bug9577427
### Environment and OS details:
Version: 1.97.0-insider (user setup)
Windows 11 Enterprise Version 24H2
OS Build: 26100.2605
### Repro Steps:
1. Open Visual Studio Code Insiders editor.
2. Tab till Copilot chat Window and press enter.
3. Navigate to Chat(Ctrl+Alt+I) in Left Nav and and activate it.
4. Navigate to Pick Model and press enter.
5. Select the any List item.
6. Observe that when a list item is selected in Pick Model, the list box closes and reopens without any user interaction.
### Actual Result:
When a list item is selected in Pick Model, the list box closes and reopens without any user interaction.
### Expected Result:
Upon selecting an item in the Pick Model list, the list box should close and remain closed until further user interaction occurs.
### User Impact:
Users will face difficulty if when a list item is selected in Pick Model, the list box closes and reopens without any user interaction.
### Attachment:
| bug,accessibility,windows | low | Critical |
2,765,729,283 | transformers | Possible bug when using cosine lr scheduler with gradient accumulation | ### System Info
transforme 4.47
deepspeed
### Who can help?
@muellerzr @SunMarc
### Information
- [ ] The official example scripts
- [ ] My own modified scripts
### Tasks
- [ ] An officially supported task in the `examples` folder (such as GLUE/SQuAD, ...)
- [ ] My own task or dataset (give details below)
[UPDATE} Turns out the issue is that I need to explicitly set "gradient_accumulation_steps": "auto" in the deepspeed config. Initially in my config I set most things to "auto" but I did not set gradient_accumulation_steps explictly, assuming it will be treated the same way as auto, otherwise will report error. FYI, would appreciate any good resource on what other parameters should be set as "auto" in deepspeed config.... I have not found a good reference. Thanks!
### Reproduction
I am running a trianing script with deepspeed as
```
deepspeed training.py
```
When using official trainer with gradient_accumulation_steps = 2 and lr_scheduler_type = cosine, I got following learning rate curve (training epoch = 1):
So seems the scheduler stepped more than one cycle. When digging through the source code, seems the issue is that in:
```
def _get_cosine_schedule_with_warmup_lr_lambda(
current_step: int, *, num_warmup_steps: int, num_training_steps: int, num_cycles: float, min_lr_rate: float = 0.0
):
if current_step < num_warmup_steps:
return float(current_step) / float(max(1, num_warmup_steps))
progress = float(current_step - num_warmup_steps) / float(max(1, num_training_steps - num_warmup_steps))
factor = 0.5 * (1.0 + math.cos(math.pi * float(num_cycles) * 2.0 * progress))
factor = factor * (1 - min_lr_rate) + min_lr_rate
return max(0, factor)
```
num_training_steps is
```
num_update_steps_per_epoch = len_dataloader // args.gradient_accumulation_steps
max_steps = math.ceil(args.num_train_epochs * num_update_steps_per_epoch)
self.create_optimizer_and_scheduler(num_training_steps=max_steps)
self.create_scheduler(num_training_steps=num_training_steps, optimizer=optimizer)
```
Therefore current_step is the global step without taking into account for gradient_accumulation, while num_training_steps did account for gradient_accumulation. As an example, if we train 1000 cases on one GPU for 1 epoch with a accumulation step of 2, the num_training_steps is 500, but current_step can go up to 1000.
Wondering if this is expected behavior or something that should be fixed?
Many thanks.
### Expected behavior
| bug | low | Critical |
2,765,794,182 | rust | slice::contains is not general in the key like HashMap::get | <!--
Thank you for filing a bug report! 🐛 Please provide a short summary of the bug,
along with any information you feel relevant to replicating the bug.
-->
I tried this code:
```rust
fn main() {
let words = ["hello", "world"].map(|s| s.to_string());
// this works fine
let hm: std::collections::HashMap<String, usize> = words
.iter()
.cloned()
.zip(words.iter().map(|w| w.len()))
.collect();
assert_eq!(hm.get("hello"), Some(&5));
// this does NOT work
assert!(words.contains("hello"));
// but has this simple workaround
assert!(words.iter().any(|e| e == "hello"));
}
```
I expected to see this happen: works
Instead, this happened: slice::contains does not accept a `&str` instead of a `&String`, like HashMap::get does. I tried searching for older issues to see if there may be a good reason for this, but I did not find anything.
| T-libs,C-discussion | low | Critical |
2,765,809,205 | tensorflow | Mixing Keras Layers and TF modules. | ### Issue type
Support
### Have you reproduced the bug with TensorFlow Nightly?
Yes
### Source
source
### TensorFlow version
2.17
### Custom code
Yes
### OS platform and distribution
Linux Ubuntu 22.04
### Mobile device
_No response_
### Python version
3.12
### Bazel version
_No response_
### GCC/compiler version
_No response_
### CUDA/cuDNN version
_No response_
### GPU model and memory
_No response_
### Current behavior?
tf.Module can trace tf.Variable but it cannot trace variables from tf.keras or tf.keras.Variable.
### Standalone code to reproduce the issue
```shell
class MockLayer(tf.Module):
def __init__(self, *args, **kwargs):
super().__init__(*args, **kwargs)
self.m = tf.keras.Variable(tf.random.normal([5, 5]), name="m")
self.w = tf.keras.Variable(tf.random.normal([5, 5]), name="w")
def __call__(self, inputs):
return self.m * inputs
layer1 = MockLayer()
print([v.name for v in layer1.trainable_variables])
```
is empty.
```
class MockLayer(tf.Module):
def __init__(self, *args, **kwargs):
super().__init__(*args, **kwargs)
self.m = tf.Variable(tf.random.normal([5, 5]), name="m")
self.w = tf.Variable(tf.random.normal([5, 5]), name="w")
def __call__(self, inputs):
return self.m * inputs
layer1 = MockLayer()
print([v.name for v in layer1.trainable_variables])
```
Works.
Specifically I am more interested in keras layers like
```
class MockLayer(tf.Module):
def __init__(self, *args, **kwargs):
super().__init__(*args, **kwargs)
self.norm = tf.keras.layers.LayerNormalization(*args, **kwargs)
def __call__(self, inputs):
return self.norm(inputs)
```
For which tracing does not appear to work.
I am interested in trying https://github.com/google/sequence-layers but they seem mostly broken on this TF version and python version due to the tracing issues.
I am curious to try fixing it, but not sure what's a supported path. Using keras layers in tf.Module does not work due to tracing issues.. and using Keras layers only does not work because Keras is missing many features like composite tensors.
Is there a way around this? :)
```
### Relevant log output
_No response_ | type:support,comp:keras,2.17 | low | Critical |
2,765,815,836 | ollama | Allow use of locally installed CUDA or ROCm | Ollama tries to install its own copy of CUDA or ROCm, even when the same version is already installed as a system-wide installation | feature request | low | Minor |
2,765,827,315 | vscode | When trying to open a 300MB log file the VCD Crashes | <!-- Failed to upload "fake_log.log" -->
<!-- Failed to upload "300MB_log.log" -->
Type: <b>Bug</b>
When trying to open a 300MB log file the VCD Crashes
The window terminated unexpectedly (reason "crashed", code:'132')
With a log file of 50MB it doesnt crash.
VS Code version: Code 1.96.2 (..., 2024-12-19T10:22:47.216Z)
OS version: Linux x64 6.8.0-49-generic
Modes:
<details>
<summary>System Info</summary>
|Item|Value|
|---|---|
|CPUs|11th Gen Intel(R) Core(TM) i7-11850H @ 2.50GHz (16 x 1093)|
|GPU Status|2d_canvas: enabled<br>canvas_oop_rasterization: enabled_on<br>direct_rendering_display_compositor: disabled_off_ok<br>gpu_compositing: enabled<br>multiple_raster_threads: enabled_on<br>opengl: enabled_on<br>rasterization: enabled<br>raw_draw: disabled_off_ok<br>skia_graphite: disabled_off<br>video_decode: enabled<br>video_encode: disabled_software<br>vulkan: disabled_off<br>webgl: enabled<br>webgl2: enabled<br>webgpu: disabled_off<br>webnn: disabled_off|
|Load (avg)|4, 5, 4|
|Memory (System)|62.53GB (43.42GB free)|
|Process Argv|--crash-reporter-id f48e985a-bee3-49a4-8365-e242b141d0c3|
|Screen Reader|no|
|VM|0%|
|DESKTOP_SESSION|ubuntu|
|XDG_CURRENT_DESKTOP|Unity|
|XDG_SESSION_DESKTOP|ubuntu|
|XDG_SESSION_TYPE|x11|
</details><details><summary>Extensions (27)</summary>
Extension|Author (truncated)|Version
---|---|---
Bookmarks|ale|13.5.0
gitlens|eam|16.0.0
copilot|Git|1.245.0
copilot-chat|Git|0.22.2
vscode-github-actions|git|0.27.0
debugpy|ms-|2024.10.0
python|ms-|2024.20.0
vscode-pylance|ms-|2024.9.1
remote-containers|ms-|0.388.0
remote-ssh|ms-|0.116.0
remote-ssh-edit|ms-|0.87.0
cmake-tools|ms-|1.19.52
cpptools|ms-|1.22.11
cpptools-extension-pack|ms-|1.3.0
makefile-tools|ms-|0.11.13
remote-explorer|ms-|0.4.3
java|red|1.37.0
code-spell-checker|str|3.0.1
cmake|twx|0.0.17
intellicode-api-usage-examples|Vis|0.2.9
vscodeintellicode|Vis|1.3.2
vscode-gradle|vsc|3.16.4
vscode-java-debug|vsc|0.58.1
vscode-java-dependency|vsc|0.24.1
vscode-java-pack|vsc|0.29.0
vscode-java-test|vsc|0.43.0
vscode-maven|vsc|0.44.0
(1 theme extensions excluded)
</details><details>
<summary>A/B Experiments</summary>
```
vsliv368cf:30146710
vspor879:30202332
vspor708:30202333
vspor363:30204092
vscod805cf:30301675
binariesv615:30325510
vsaa593:30376534
py29gd2263:31024239
c4g48928:30535728
azure-dev_surveyone:30548225
962ge761:30959799
pythonnoceb:30805159
pythonmypyd1:30879173
h48ei257:31000450
pythontbext0:30879054
cppperfnew:31000557
dsvsc020:30976470
pythonait:31006305
dsvsc021:30996838
dvdeprecation:31068756
dwnewjupyter:31046869
newcmakeconfigv2:31071590
nativerepl2:31139839
pythonrstrctxt:31112756
nativeloc2:31192216
cf971741:31144450
iacca1:31171482
notype1:31157159
5fd0e150:31155592
dwcopilot:31170013
stablechunks:31184530
6074i472:31201624
```
</details>
<!-- generated by issue reporter --><!-- Failed to upload "fake_log.log" -->
First time [the bug has been reported for 1.96.1](https://github.com/microsoft/vscode/issues/236568).
| freeze-slow-crash-leak | low | Critical |
2,765,833,157 | go | net: TestDialListenerAddr failures | ```
#!watchflakes
default <- pkg == "net" && test == "TestDialListenerAddr"
```
Issue created automatically to collect these failures.
Example ([log](https://ci.chromium.org/b/8726880560451781425)):
=== RUN TestDialListenerAddr
dial_test.go:964: listening on "127.0.0.1:64007"
dial_test.go:982: Dial("tcp4", "[::]:64007"): dial tcp4 0.0.0.0:64007: connect: connection refused
--- FAIL: TestDialListenerAddr (0.00s)
— [watchflakes](https://go.dev/wiki/Watchflakes)
| NeedsInvestigation | low | Critical |
2,765,839,328 | flutter | CarouselView cards animation changes after widget gets recreated | ### Steps to reproduce
1. Run provided code.
2. Swipe cards - they are animated correctly.
3. Click swipe icon twice what disposes and creates CarouselView.
4. Swipe cards - they are resized instead of moved.
### Expected results
I expect that cards will be not resized while swiping.
https://github.com/user-attachments/assets/de23253b-7499-4e90-b5e6-57053ea58007
### Actual results
Cards are resized while swiping.
https://github.com/user-attachments/assets/975d719b-895e-4666-987d-e2fb4822ac5e
### Code sample
<details open><summary>Code sample</summary>
```dart
import 'package:flutter/material.dart';
void main() {
runApp(const MyApp());
}
class MyApp extends StatelessWidget {
const MyApp({super.key});
@override
Widget build(BuildContext context) {
return MaterialApp(
title: 'Flutter Demo',
theme: ThemeData(
colorScheme: ColorScheme.fromSeed(seedColor: Colors.deepPurple),
useMaterial3: true,
),
home: const Scaffold(
body: SafeArea(
child: PageSwiper(),
)));
}
}
class PageSwiper extends StatefulWidget {
const PageSwiper({super.key});
@override
State<PageSwiper> createState() => _PageSwiperState();
}
class _PageSwiperState extends State<PageSwiper> {
int page = 0;
@override
Widget build(BuildContext context) {
return Column(
children: [
IconButton(onPressed: () => setState(() => page = page == 0 ? 1 : 0), icon: const Icon(Icons.swipe)),
page == 0
? SizedBox(
height: 150,
child: CarouselView(
scrollDirection: Axis.horizontal,
itemSnapping: true,
itemExtent: double.infinity,
children: [1, 2].map((e) => HomepageBoostedOddsCarouselCard(index: e)).toList(),
),
)
: Container(),
],
);
}
}
class HomepageBoostedOddsCarouselCard extends StatelessWidget {
const HomepageBoostedOddsCarouselCard({
super.key,
required this.index,
});
final int index;
@override
Widget build(BuildContext context) {
return Container(
color: Colors.amber,
child: Column(
crossAxisAlignment: CrossAxisAlignment.center,
mainAxisSize: MainAxisSize.min,
children: [
const Text('New design'),
const SizedBox(height: 10),
Container(color: Colors.white, height: 30, width: 200),
const SizedBox(height: 10),
],
),
);
}
}
```
</details>
### Screenshots or Video
<details open>
<summary>Screenshots / Video demonstration</summary>
[[Upload media here]](https://github.com/user-attachments/assets/b32b7986-cc74-4706-a915-23bd482201c6)
</details>
### Logs
<details open><summary>Logs</summary>
```console
[Paste your logs here]
```
</details>
### Flutter Doctor output
<details open><summary>Doctor output</summary>
```console
[✓] Flutter (Channel stable, 3.24.1, on macOS 15.2 24C101 darwin-arm64, locale en-PL)
• Flutter version 3.24.1 on channel stable at /Users/kris/flutter
• Upstream repository https://github.com/flutter/flutter.git
• Framework revision 5874a72aa4 (5 months ago), 2024-08-20 16:46:00 -0500
• Engine revision c9b9d5780d
• Dart version 3.5.1
• DevTools version 2.37.2
[!] Android toolchain - develop for Android devices (Android SDK version 35.0.0)
• Android SDK at /Users/kris/Library/Android/sdk
✗ cmdline-tools component is missing
Run `path/to/sdkmanager --install "cmdline-tools;latest"`
See https://developer.android.com/studio/command-line for more details.
✗ Android license status unknown.
Run `flutter doctor --android-licenses` to accept the SDK licenses.
See https://flutter.dev/to/macos-android-setup for more details.
[✓] Xcode - develop for iOS and macOS (Xcode 16.1)
• Xcode at /Applications/Xcode.app/Contents/Developer
• Build 16B40
• CocoaPods version 1.15.2
[✓] Chrome - develop for the web
• Chrome at /Applications/Google Chrome.app/Contents/MacOS/Google Chrome
[✓] Android Studio (version 2024.1)
• Android Studio at /Applications/Android Studio.app/Contents
• Flutter plugin can be installed from:
🔨 https://plugins.jetbrains.com/plugin/9212-flutter
• Dart plugin can be installed from:
🔨 https://plugins.jetbrains.com/plugin/6351-dart
• Java version OpenJDK Runtime Environment (build 17.0.11+0-17.0.11b1207.24-11852314)
[✓] VS Code (version 1.96.2)
• VS Code at /Applications/Visual Studio Code.app/Contents
• Flutter extension version 3.102.0
```
</details>
| framework,f: material design,has reproducible steps,P2,team-design,triaged-design,found in release: 3.27,found in release: 3.28 | low | Minor |
2,765,840,405 | go | proposal: log/slog: native support for handling List | ### Proposal Details
The current implementation of `log/slog` does not fully support logging arrays or slices. As a result, the type implementing the `slog.Valuer` interface is not respected when passed as an element of an array or slice and the `Handler` cannot handle the elements within the input array or slice either.
One possible workaround is to create a custom `List` using a generic struct that implements the `slog.LogValuer` interface, returns a `Group` and uses the index as the key. An example of this approach can be found in this comment https://github.com/golang/go/issues/63204#issuecomment-2428962553
However, it would make more sense and be more practical if `List` were natively supported
```go
type listptr *Value // used in Value.any when the Value is a []Value
const (
KindAny Kind = iota
KindBool
KindDuration
KindFloat64
KindInt64
KindString
KindTime
KindUint64
KindGroup
KindLogValuer
KindList
)
// ListValue returns a [Value] for a slice of arbitrary values.
func ListValue(vs ...Value) Value {
return Value{num: uint64(len(vs)), any: listptr(unsafe.SliceData(vs))}
}
// List returns v's value as a []Value.
// It panics if v's [Kind] is not [KindList].
func (v Value) List() []Value{
if sp, ok := v.any.(listptr); ok {
return unsafe.Slice((*Value)(sp), v.num)
}
panic("List: bad kind")
}
func (v Value) list() []Value{
return unsafe.Slice((*Value)(v.any.(listptr)), v.num)
}
``` | Proposal | low | Major |
2,765,847,332 | vscode | Make the activity icons toggleable when on top (and bottom) | <!-- ⚠️⚠️ Do Not Delete This! feature_request_template ⚠️⚠️ -->
<!-- Please read our Rules of Conduct: https://opensource.microsoft.com/codeofconduct/ -->
<!-- Please search existing issues to avoid creating duplicates. -->
<!-- Describe the feature you'd like. -->
Hi there :)
I like to enable and disable a certain view, when I click on its icon.
That is already possible when the icon of said activity is on the side with the default setting.
The top/setting seems to not have that.
https://github.com/user-attachments/assets/04aebe11-e7da-4f85-b8c7-74250f94e280
| feature-request,workbench-views | low | Major |
2,765,870,241 | storybook | [Tracking] Typesafe CSF factories | Tracking issue to implement the following RFC::
https://github.com/storybookjs/storybook/discussions/30112
```[tasklist]
### Create a POC where all pieces are working together (by week 2)
- [x] API
- [x] Basic type safety for React
- [x] Runtime
- [x] AST
- [ ] https://github.com/storybookjs/storybook/issues/30169
- [ ] https://github.com/storybookjs/storybook/issues/30173
- [ ] https://github.com/storybookjs/storybook/issues/30175
- [x] Vitest
- [x] CLI templates only for sandboxes + minimal codemod
- [x] Basic codemod
- [ ] https://github.com/storybookjs/storybook/issues/30170
- [ ] https://github.com/storybookjs/storybook/issues/30244
- [ ] https://github.com/storybookjs/storybook/issues/30241
- [x] Test runner
- [x] QA
```
```[tasklist]
### Convert to releasable form (by week 5)
- [ ] https://github.com/storybookjs/storybook/issues/30243
- [ ] https://github.com/storybookjs/storybook/issues/30239
- [ ] https://github.com/storybookjs/storybook/issues/30240
- [ ] https://github.com/storybookjs/storybook/issues/30316
- [ ] https://github.com/storybookjs/storybook/issues/30357
- [ ] https://github.com/storybookjs/storybook/issues/30242
- [ ] https://github.com/storybookjs/storybook/issues/30235
- [ ] https://github.com/storybookjs/storybook/issues/30236
- [ ] https://github.com/storybookjs/storybook/issues/30237
- [ ] https://github.com/storybookjs/storybook/issues/30238
- [ ] Transform args, parameters and play into root properties as getters + deprecation message to use .input instead
- [x] use csf-2-to-3 codemod as part of csf-factories codemod
```
```[tasklist]
### Docs
- [ ] https://github.com/storybookjs/storybook/issues/30329
- [ ] https://github.com/storybookjs/storybook/issues/30342
- [ ] https://github.com/storybookjs/storybook/issues/30383
```
```[tasklist]
### Nice to have milestone
- [ ] Implement Jeppe's proposal to get rid of essentials
- [ ] Implement other renderers
- [ ] Refactor ESLint to use csf-tools and implement CSF factory features
- [ ] Shrink the react docs entrypoint
- [ ] Advanced type safety
- [ ] Third party Addons
- [ ] Write new story file with CSF factory in "Add new component" feature if preview file uses csf factory
```
| feature request,csf,Tracking | low | Minor |
2,765,874,546 | bitcoin | Fuzz: Runtime errors when running fuzz tests on MacOs | ### Is there an existing issue for this?
- [X] I have searched the existing issues
### Current behaviour
Whenever running any fuzz test on any fuzz target on MacOs according to the steps provided [here](https://github.com/bitcoin/bitcoin/issues/31049). There is a big error log being thrown before starting the fuzz tests. To be noted that the fuzz tests run fine afterwards.
### Expected behaviour
No error is thrown and fuzz tests run as expected.
### Steps to reproduce
Set up environment variables for LLVM 18
```
export LDFLAGS="-L$(brew --prefix llvm@18)/lib -L$(brew --prefix llvm@18)/lib/c++ -L$(brew --prefix llvm@18)/lib/unwind -lunwind"
export CPPFLAGS="-I$(brew --prefix llvm@18)/include"
export PATH="$(brew --prefix llvm@18)/bin:$PATH"
export CC="$(brew --prefix llvm@18)/bin/clang"
export CXX="$(brew --prefix llvm@18)/bin/clang++"
```
Run CMake with the preset
```
cmake --preset=libfuzzer \
-DCMAKE_C_COMPILER="$(brew --prefix llvm@18)/bin/clang" \
-DCMAKE_CXX_COMPILER="$(brew --prefix llvm@18)/bin/clang++" \
-DAPPEND_LDFLAGS="-Wl,-no_warn_duplicate_libraries" \
-DCMAKE_EXE_LINKER_FLAGS="$LDFLAGS"
```
build and run with any fuzz target
```
cmake --build build_fuzz -j$(sysctl -n hw.ncpu)
FUZZ=process_message build_fuzz/src/test/fuzz/fuzz
```
### Relevant log output
```
/opt/homebrew/opt/llvm@18/bin/../include/c++/v1/variant:495:12: runtime error: call to function decltype(auto) std::__1::__variant_detail::__visitation::__base::__dispatcher<0ul, 0ul>::__dispatch[abi:ne180100]<void std::__1::__variant_detail::__ctor<std::__1::__variant_detail::__traits<RPCArg::Optional, std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>>, UniValue>>::__generic_construct[abi:ne180100]<std::__1::__variant_detail::__move_constructor<std::__1::__variant_detail::__traits<RPCArg::Optional, std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>>, UniValue>, (std::__1::__variant_detail::_Trait)1>>(std::__1::__variant_detail::__ctor<std::__1::__variant_detail::__traits<RPCArg::Optional, std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>>, UniValue>>&, std::__1::__variant_detail::__move_constructor<std::__1::__variant_detail::__traits<RPCArg::Optional, std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>>, UniValue>, (std::__1::__variant_detail::_Trait)1>&&)::'lambda'(std::__1::__variant_detail::__move_constructor<std::__1::__variant_detail::__traits<RPCArg::Optional, std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>>, UniValue>, (std::__1::__variant_detail::_Trait)1>&, auto&&)&&, std::__1::__variant_detail::__base<(std::__1::__variant_detail::_Trait)1, RPCArg::Optional, std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>>, UniValue>&, std::__1::__variant_detail::__base<(std::__1::__variant_detail::_Trait)1, RPCArg::Optional, std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>>, UniValue>&&>(std::__1::__variant_detail::__move_constructor<std::__1::__variant_detail::__traits<RPCArg::Optional, std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>>, UniValue>, (std::__1::__variant_detail::_Trait)1>, std::__1::__variant_detail::__base<(std::__1::__variant_detail::_Trait)1, RPCArg::Optional, std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>>, UniValue>&, std::__1::__variant_detail::__base<(std::__1::__variant_detail::_Trait)1, RPCArg::Optional, std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>>, UniValue>&&) through pointer to incorrect function type 'void (*)((lambda at /opt/homebrew/opt/llvm@18/bin/../include/c++/v1/variant:814:11) &&, std::__variant_detail::__base<std::__variant_detail::_Trait::_Available, RPCArg::Optional, std::string, UniValue> &, std::__variant_detail::__base<std::__variant_detail::_Trait::_Available, RPCArg::Optional, std::string, UniValue> &&)'
variant:532: note: decltype(auto) std::__1::__variant_detail::__visitation::__base::__dispatcher<0ul, 0ul>::__dispatch[abi:ne180100]<void std::__1::__variant_detail::__ctor<std::__1::__variant_detail::__traits<RPCArg::Optional, std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>>, UniValue>>::__generic_construct[abi:ne180100]<std::__1::__variant_detail::__move_constructor<std::__1::__variant_detail::__traits<RPCArg::Optional, std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>>, UniValue>, (std::__1::__variant_detail::_Trait)1>>(std::__1::__variant_detail::__ctor<std::__1::__variant_detail::__traits<RPCArg::Optional, std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>>, UniValue>>&, std::__1::__variant_detail::__move_constructor<std::__1::__variant_detail::__traits<RPCArg::Optional, std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>>, UniValue>, (std::__1::__variant_detail::_Trait)1>&&)::'lambda'(std::__1::__variant_detail::__move_constructor<std::__1::__variant_detail::__traits<RPCArg::Optional, std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>>, UniValue>, (std::__1::__variant_detail::_Trait)1>&, auto&&)&&, std::__1::__variant_detail::__base<(std::__1::__variant_detail::_Trait)1, RPCArg::Optional, std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>>, UniValue>&, std::__1::__variant_detail::__base<(std::__1::__variant_detail::_Trait)1, RPCArg::Optional, std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>>, UniValue>&&>(std::__1::__variant_detail::__move_constructor<std::__1::__variant_detail::__traits<RPCArg::Optional, std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>>, UniValue>, (std::__1::__variant_detail::_Trait)1>, std::__1::__variant_detail::__base<(std::__1::__variant_detail::_Trait)1, RPCArg::Optional, std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>>, UniValue>&, std::__1::__variant_detail::__base<(std::__1::__variant_detail::_Trait)1, RPCArg::Optional, std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>>, UniValue>&&) defined here
SUMMARY: UndefinedBehaviorSanitizer: undefined-behavior /opt/homebrew/opt/llvm@18/bin/../include/c++/v1/variant:495:12
/Users/prabhatverma/projects/bitcoin/src/rpc/server.h:100:15: runtime error: call to function getblockchaininfo() through pointer to incorrect function type 'RPCHelpMan (*)()'
blockchain.cpp:1288: note: getblockchaininfo() defined here
SUMMARY: UndefinedBehaviorSanitizer: undefined-behavior /Users/prabhatverma/projects/bitcoin/src/rpc/server.h:100:15
/Users/prabhatverma/projects/bitcoin/src/rpc/server.h:102:15: runtime error: call to function getblockchaininfo() through pointer to incorrect function type 'RPCHelpMan (*)()'
blockchain.cpp:1288: note: getblockchaininfo() defined here
SUMMARY: UndefinedBehaviorSanitizer: undefined-behavior /Users/prabhatverma/projects/bitcoin/src/rpc/server.h:102:15
/Users/prabhatverma/projects/bitcoin/src/tinyformat.h:537:13: runtime error: call to function void tinyformat::detail::FormatArg::formatImpl<char [13]>(std::__1::basic_ostream<char, std::__1::char_traits<char>>&, char const*, char const*, int, void const*) through pointer to incorrect function type 'void (*)(std::ostream &, const char *, const char *, int, const void *)'
tinyformat.h:551: note: void tinyformat::detail::FormatArg::formatImpl<char [13]>(std::__1::basic_ostream<char, std::__1::char_traits<char>>&, char const*, char const*, int, void const*) defined here
SUMMARY: UndefinedBehaviorSanitizer: undefined-behavior /Users/prabhatverma/projects/bitcoin/src/tinyformat.h:537:13
INFO: Running with entropic power schedule (0xFF, 100).
INFO: Seed: 1726115676
INFO: Loaded 1 modules (1253576 inline 8-bit counters): 1253576 [0x1059e58c8, 0x105b17990),
INFO: Loaded 1 PC tables (1253576 PCs): 1253576 [0x105b17990,0x106e38610),
INFO: -max_len is not provided; libFuzzer will not generate inputs larger than 4096 bytes
/opt/homebrew/opt/llvm@18/bin/../include/c++/v1/__type_traits/invoke.h:344:25: runtime error: call to function process_message_fuzz_target(std::__1::span<unsigned char const, 18446744073709551615ul>) through pointer to incorrect function type 'void (*)(std::span<const unsigned char>)'
process_message.cpp:54: note: process_message_fuzz_target(std::__1::span<unsigned char const, 18446744073709551615ul>) defined here
SUMMARY: UndefinedBehaviorSanitizer: undefined-behavior /opt/homebrew/opt/llvm@18/bin/../include/c++/v1/__type_traits/invoke.h:344:25
INFO: A corpus is not provided, starting from an empty corpus
#2 INITED cov: 2751 ft: 2749 corp: 1/1b exec/s: 0 rss: 187Mb
#3 NEW cov: 2757 ft: 2851 corp: 2/2b lim: 4 exec/s: 0 rss: 187Mb L: 1/1 MS: 1 ChangeByte-
#5 NEW cov: 2757 ft: 2855 corp: 3/4b lim: 4 exec/s: 0 rss: 187Mb L: 2/2 MS: 2 CrossOver-InsertByte-
```
### How did you obtain Bitcoin Core
Compiled from source
### What version of Bitcoin Core are you using?
master@bb57017b2945d5e0bbd95c7f1a9369a8ab7c6fcd
### Operating system and version
MacOs Sequioa 15.1.1
### Machine specifications
Silicon Macbook Pro
Chip - M4 Pro
Memory - 24 gb (14 core cpu , 20 core gpu) | macOS,Tests | low | Critical |
2,765,877,523 | godot | You can only copy a scene path once. | ### Tested versions
v4.4.dev7.official [46c8f8c5c]
v3.6.stable.official [de2f0f147]
### System information
win11
### Issue description
You cannot copy a scene path again using the shortcut CTRL + SHIFT + C if you copy any other text immediately after.
To copy the scene path again, deselect the scene (in the "File System" dock) and select it again, then you can copy the scene path using the shortcut.
### Steps to reproduce
1. Select a scene in the "File System" dock.
2. Copy its path using the shortcut CTRL + SHIFT + C.
3. Paste the text and verify that the path was copied.
4. Copy any other text, such as the name of a node. The scene from which you copied the path remains selected.
5. Go back to the scene that remains selected in the "File System" (Click on the scene, although it will remain selected) dock and try copying its path again using CTRL + SHIFT + C.
6. Paste the copied path and you will see that it was not copied.
### Minimal reproduction project (MRP)
... | bug,topic:editor | low | Minor |
2,765,883,807 | kubernetes | can MountPath contain ":" ? | ### What happened?
https://github.com/kubernetes/kubernetes/blob/master/pkg/apis/core/types.go#L2110-L2113
```
RecursiveReadOnly *RecursiveReadOnlyMode
// Required. If the path is not an absolute path (e.g. some/path) it
// will be prepended with the appropriate root prefix for the operating
// system. On Linux this is '/', on Windows this is 'C:\'.
MountPath string
```
but
https://github.com/kubernetes/kubernetes/blob/master/staging/src/k8s.io/api/core/v1/types.go#L2283
```
// Path within the container at which the volume should be mounted. Must
// not contain ':'.
MountPath string `json:"mountPath" protobuf:"bytes,3,opt,name=mountPath"`
```
some people use mountpath:/etc/localtime:ro (k8s should use readonly:true) will not work on containerd but work on docker.
### What did you expect to happen?
mountPath can't contain ":"
### How can we reproduce it (as minimally and precisely as possible)?
set mountpath:/etc/localtime:ro
### Anything else we need to know?
_No response_
### Kubernetes version
any
### Cloud provider
no
### OS version
<details>
```console
# On Linux:
$ cat /etc/os-release
# paste output here
$ uname -a
# paste output here
# On Windows:
C:\> wmic os get Caption, Version, BuildNumber, OSArchitecture
# paste output here
```
</details>
### Install tools
<details>
</details>
### Container runtime (CRI) and version (if applicable)
<details>
</details>
### Related plugins (CNI, CSI, ...) and versions (if applicable)
<details>
</details>
| kind/bug,priority/backlog,sig/storage,sig/node,sig/windows,triage/accepted | medium | Major |
2,765,915,844 | go | net: TestDialLocal failures | ```
#!watchflakes
default <- pkg == "net" && test == "TestDialLocal"
```
Issue created automatically to collect these failures.
Example ([log](https://ci.chromium.org/b/8726880560451781425)):
=== RUN TestDialLocal
dial_test.go:71: dial tcp :64041: connect: connection refused
--- FAIL: TestDialLocal (0.00s)
— [watchflakes](https://go.dev/wiki/Watchflakes)
| NeedsInvestigation | low | Critical |
2,765,927,156 | ollama | The <toolcall> in nemotron-mini. Again. | ### What is the issue?
# The problem
I am trying to implement the agent swarm for ollama from scratch. I made the triage agent: the intent navigator. It should call the `navigate_to_refund_agent_tool` or `navigate_to_sales_agent_tool` depends on user's choose. Both tools got empty arguments like
```tsx
function navigate_to_refund_agent_tool(/* no arguments */) {
}
function navigate_to_sales_agent_tool(/* no arguments */) {
}
```
When I send the following curl request it return the nasty XML output.
```bash
curl --location 'http://localhost:11434/api/chat' \
--header 'Content-Type: application/json' \
--data '{
"model": "nemotron-mini",
"messages": [
{
"role": "system",
"content": "You are to triage a users request, and call a tool to transfer to the right agent. There are two agents you can transfer to: navigate_to_refund_agent_tool and navigate_to_sales_agent_tool. Untill calling any function, you must ask the user for their agent. Before navigation make sure you choose well. Do not spam function executions"
},
{
"role": "user",
"content": "Navigate me to sales agent"
}
],
"stream": false,
"options": {
"top_k": 20,
"top_p": 0.4,
"temperature": 0.5
},
"tools": [
{
"type": "function",
"function": {
"name": "navigate_to_sales_agent_tool",
"description": "Navigate to sales agent",
"parameters": {
"type": "object",
"required": [
],
"properties": {
}
}
}
},
{
"type": "function",
"function": {
"name": "navigate_to_refund_agent_tool",
"description": "Navigate to refund agent",
"parameters": {
"type": "object",
"required": [
],
"properties": {
}
}
}
}
]
}'
```
Time-to-time the output is
```
<toolcall> {\"type\": \"function\", \"arguments\": { \"name\": \"navigate_to_sales_agent_tool\" }} </toolcall>
```
Also, sometimes the JSON in `<toolcall>` tag is invalid
# To solve the problem
1. **How do I hardcode the model version? I am seeing you are updating models without publishing the new tag**
This is definitely going to break the AI prompts, I need to fetch exactly the defined model version even if it was uploaded 10 years ago
2. **When are you planning to clear all fake labels with tools support?**
The XML output is a real common for all models with tools in the list. This is a fake. Give me the truly information about the state of the framework: without tools it unusable and pointless waste of time
### OS
Linux
### GPU
Nvidia
### CPU
Intel
### Ollama version
0.5.4 | bug | medium | Critical |
2,765,953,153 | ollama | Enable auto-save functionality via CLI flag | Having ollama models keep track of past conversations improves the quality of answers dramatically. Using `/save <model>` manually with every run is time-consuming, and prone to be forgotten. Allowing a flag similar to `ollama run --auto-save-on-exit <model>` would make this process a lot smoother. The solutions proposed on https://github.com/ollama/ollama/issues/1238 and https://github.com/ollama/ollama/issues/3800 are not sufficient to satisfy this feature request.
Thank you for the hard work already done 🙏 | feature request | low | Minor |
2,765,959,954 | vscode | Ctrl + C not working |
Type: <b>Bug</b>
When I use Ctrl+C to copy the command line in a Python file, it doesn't copy the selected content. However, right-clicking and copying works fine, and the Ctrl+V shortcut can still paste normally. I have already tried disabling all extensions (by invoking the command 'Reload with Extensions Disabled' from the command palette (press F1 to open the command palette)), but Ctrl+C still doesn't work.
VS Code version: Code 1.96.2 (fabdb6a30b49f79a7aba0f2ad9df9b399473380f, 2024-12-19T10:22:47.216Z)
OS version: Windows_NT x64 10.0.22631
Modes:
Remote OS version: Linux x64 5.15.0-127-generic
<details>
<summary>System Info</summary>
|Item|Value|
|---|---|
|CPUs|AMD Ryzen 7 5800 8-Core Processor (16 x 3394)|
|GPU Status|2d_canvas: enabled<br>canvas_oop_rasterization: enabled_on<br>direct_rendering_display_compositor: disabled_off_ok<br>gpu_compositing: enabled<br>multiple_raster_threads: enabled_on<br>opengl: enabled_on<br>rasterization: enabled<br>raw_draw: disabled_off_ok<br>skia_graphite: disabled_off<br>video_decode: enabled<br>video_encode: enabled<br>vulkan: disabled_off<br>webgl: enabled<br>webgl2: enabled<br>webgpu: enabled<br>webnn: disabled_off|
|Load (avg)|undefined|
|Memory (System)|79.87GB (66.74GB free)|
|Process Argv|--crash-reporter-id c3359fec-6af1-4b51-9484-8098dd1da00e|
|Screen Reader|no|
|VM|0%|
|Item|Value|
|---|---|
|Remote|SSH: SLab-GPU4|
|OS|Linux x64 5.15.0-127-generic|
|CPUs|Intel(R) Xeon(R) Gold 6326 CPU @ 2.90GHz (64 x 800)|
|Memory (System)|247.55GB (241.43GB free)|
|VM|0%|
</details><details><summary>Extensions (35)</summary>
Extension|Author (truncated)|Version
---|---|---
jupyter-keymap|ms-|1.1.2
remote-containers|ms-|0.394.0
remote-ssh|ms-|0.116.1
remote-ssh-edit|ms-|0.87.0
remote-wsl|ms-|0.88.5
vscode-remote-extensionpack|ms-|0.26.0
remote-explorer|ms-|0.5.2024121609
remote-server|ms-|1.5.2
pytorch-snippets|SBS|1.0.2
latex-support|tor|3.10.0
vscode-icons|vsc|12.10.0
material-theme|zhu|3.17.7
vscode-markdownlint|Dav|0.57.0
githistory|don|0.6.20
git-project-manager|fel|1.8.2
code-runner|for|0.12.2
copilot|Git|1.254.0
copilot-chat|Git|0.23.2
vscode-pull-request-github|Git|0.102.0
gc-excelviewer|Gra|4.2.62
latex-workshop|Jam|10.7.1
vscode-latex|mat|1.3.0
rainbow-csv|mec|3.13.0
vscode-docker|ms-|1.29.3
debugpy|ms-|2024.14.0
gather|ms-|2022.3.2
isort|ms-|2023.10.1
python|ms-|2024.22.1
vscode-pylance|ms-|2024.12.1
jupyter|ms-|2024.11.0
jupyter-keymap|ms-|1.1.2
jupyter-renderers|ms-|1.0.21
vscode-jupyter-cell-tags|ms-|0.1.9
vscode-jupyter-slideshow|ms-|0.1.6
code-translate|w88|1.0.20
</details><details>
<summary>A/B Experiments</summary>
```
vsliv368cf:30146710
vspor879:30202332
vspor708:30202333
vspor363:30204092
vswsl492:30256859
vscod805:30301674
binariesv615:30325510
vsaa593cf:30376535
py29gd2263:31024239
vscaat:30438848
c4g48928:30535728
azure-dev_surveyone:30548225
962ge761:30959799
pythonnoceb:30805159
pythonmypyd1:30879173
2e7ec940:31000449
pythontbext0:30879054
cppperfnew:31000557
dsvsc020:30976470
pythonait:31006305
dsvsc021:30996838
dvdeprecation:31068756
dwnewjupyter:31046869
nativerepl2:31139839
pythonrstrctxt:31112756
nativeloc2:31192216
cf971741:31144450
iacca1:31171482
notype1cf:31157160
5fd0e150:31155592
dwcopilot:31170013
stablechunks:31184530
6074i472:31201624
```
</details>
<!-- generated by issue reporter --> | info-needed,triage-needed | low | Critical |
2,765,980,456 | flutter | Separate properties for the selected day of the DatePicker | ### Use case
Currently the Flutter engine uses the `dayOverlayColor` to assign color to the selected day button. This is not intuitive and also limits the customization of the Date Picker, since the `dayOverlayColor` and `dayBackgroundColor` must be similar, since there is no way to select the color of the text of the selected day.
Imagine the following: I'm using a white background for all dates and a blue text color.
```dart
dayBackgroundColor: Colors.white,
dayForegroundColor: Colors.blue,
```
If I set the `dayOverlayColor` to `Colors.blue`, when the user selects a date, I'd have a round blue button with, what would appear to be, no text.
### Proposal
I propose that we add the following properties:
`selectedBackgroundColor` and `selectedForegroundColor`
where both properties, similar to the ones we have today, control, respectively, the background and foreground colors of the button.
or
`selectedDayTheme`
where we could have a `ButtonStyle` to assign the colors.
I also propose that we standardize the other properties to be like the `confirmButtonStyle`, making it intuitive for the user to customize the dialog.
PS: the same thing should be done to the year buttons as well. | c: new feature,framework,f: material design,f: date/time picker,c: proposal,P3,team-design,triaged-design | low | Minor |
2,765,996,117 | node | Native addon use ThreadsafeFunction in multithreads env casue EXC_BAD_ACCESS in worker_threads in Node 18 | ### Version
v18.20.5
The Node 20, Node 22 works fine
### What steps will reproduce the bug?
The minimal reproduce example is very difficult to construct; if anyone is interested, they can check how to reproduce in the Rust project:
1. Clone `https://github.com/napi-rs/napi-rs`
2. Checkout to `12-23-feat_napi_impl_readablestream_and_asyncgenerator` branch
3. Install latest stable Rust, it's `1.83.0` at this moment
4. `corepack enable`
5. `yarn install`
6. `yarn workspace @examples/napi build`
- if you want to run test directly `yarn workspace @examples/napi test __tests__/stream.spec.ts`
- if you want to run `lldb`
- `cd examples/napi`
- `lldb node`
- `run --loader ts-node/esm/transpile-only ../../node_modules/ava/entrypoints/cli.mjs __tests__/stream.spec.ts`
lldb log:
```
lldb) bt
* thread #13, stop reason = EXC_BAD_ACCESS (code=1, address=0x10)
* frame #0: 0x00000001000803dc node`napi_env__::DeleteMe() + 52
frame #1: 0x000000010008373c node`v8impl::(anonymous namespace)::ThreadSafeFunction::~ThreadSafeFunction() + 84
frame #2: 0x0000000100083784 node`v8impl::(anonymous namespace)::ThreadSafeFunction::~ThreadSafeFunction() + 12
frame #3: 0x0000000100083980 node`void node::Environment::CloseHandle<uv_handle_s, v8impl::(anonymous namespace)::ThreadSafeFunction::CloseHandlesAndMaybeDelete(bool)::'lambda'(uv_handle_s*)>(uv_handle_s*, v8impl::(anonymous namespace)::ThreadSafeFunction::CloseHandlesAndMaybeDelete(bool)::'lambda'(uv_handle_s*))::'lambda'(uv_handle_s*)::__invoke(uv_handle_s*) + 240
frame #4: 0x000000010244a280 libuv.1.dylib`uv_run + 520
frame #5: 0x000000010005f58c node`node::Environment::CleanupHandles() + 252
frame #6: 0x000000010005fbb8 node`node::Environment::RunCleanup() + 372
frame #7: 0x000000010000beb0 node`node::FreeEnvironment(node::Environment*) + 120
frame #8: 0x000000010014371c node`node::OnScopeLeaveImpl<node::worker::Worker::Run()::$_0>::~OnScopeLeaveImpl() + 112
frame #9: 0x0000000100143390 node`node::worker::Worker::Run() + 1408
frame #10: 0x0000000100145b60 node`node::worker::Worker::StartThread(v8::FunctionCallbackInfo<v8::Value> const&)::$_0::__invoke(void*) + 56
frame #11: 0x000000018afe02e4 libsystem_pthread.dylib`_pthread_start + 136
```
### How often does it reproduce? Is there a required condition?
Very easy to reproduce.
### What is the expected behavior? Why is that the expected behavior?
Process exit with normal exit code
### What do you see instead?
After some bisects, I found the latest properly Node 18 is `18.18.2`, in the [v18.18.2..v18.19.0 diff](https://github.com/nodejs/node/compare/v18.18.2..v18.19.0), I think this PR is most likely to cause this issue https://github.com/nodejs/node/pull/42651.
### Additional information
_No response_ | node-api | low | Critical |
2,765,996,613 | angular | Optimize and Refactor the code | ### Which @angular/* package(s) are relevant/related to the feature request?
_No response_
### Description
In the Footer component, you added static code.
```
<div class="adev-footer-container">
<div class="adev-footer-columns">
<div>
<h2>Social Media</h2>
<ul>
<li>
<a [href]="MEDIUM" title="Angular blog">Blog</a>
</li>
<li>
<a [href]="X" title="X (formerly Twitter)">X (formerly Twitter)</a>
</li>
<li>
<a [href]="YOUTUBE" title="YouTube">YouTube</a>
</li>
<li>
<a
href="https://discord.gg/angular"
title="Join the discussions at Angular Community Discord server."
>
Discord
</a>
</li>
<li>
<a [href]="GITHUB" title="GitHub">GitHub</a>
</li>
<li>
<a
href="https://stackoverflow.com/questions/tagged/angular"
title="Stack Overflow: where the community answers your technical Angular questions."
>
Stack Overflow
</a>
</li>
</ul>
</div>
<div>
<h2>Community</h2>
<ul>
<li>
<a
href="https://github.com/angular/angular/blob/main/CONTRIBUTING.md"
title="Contribute to Angular"
>
Contribute
</a>
</li>
<li>
<a
href="https://github.com/angular/code-of-conduct/blob/main/CODE_OF_CONDUCT.md"
title="Treating each other with respect."
>
Code of Conduct
</a>
</li>
<li>
<a
href="https://github.com/angular/angular/issues"
title="Post issues and suggestions on github."
>
Report Issues
</a>
</li>
<li>
<a
href="https://devlibrary.withgoogle.com/products/angular?sort=updated"
title="Google's DevLibrary"
>
Google's DevLibrary
</a>
</li>
<li>
<a
href="https://developers.google.com/community/experts/directory?specialization=angular"
title="Angular Google Developer Experts"
>
Angular Google Developer Experts
</a>
</li>
</ul>
</div>
<div>
<h2>Resources</h2>
<ul>
<li>
<a routerLink="/press-kit" title="Press contacts, logos, and branding.">Press Kit</a>
</li>
<li>
<a routerLink="/roadmap" title="Roadmap">Roadmap</a>
</li>
</ul>
</div>
<div>
<h2>Languages</h2>
<ul>
<li>
<a href="https://angular.cn/" title="简体中文版">简体中文版</a>
</li>
<li>
<a href="https://angular.tw/" title="正體中文版">正體中文版</a>
</li>
<li>
<a href="https://angular.jp/" title="日本語版">日本語版</a>
</li>
<li>
<a href="https://angular.kr/" title="한국어">한국어</a>
</li>
<li>
<a
href="https://angular-gr.web.app"
title="Ελληνικά"
>
Ελληνικά
</a>
</li>
</ul>
</div>
</div>
<p class="docs-license">
Super-powered by Google ©2010-2024. Code licensed under an
<a routerLink="/license" title="License text">MIT-style License</a>
. Documentation licensed under
<a href="https://creativecommons.org/licenses/by/4.0/">CC BY 4.0</a>
.
</p>
</div>
```
### Proposed solution
Solution :
**footer.component.html**
```
<div class="adev-footer-container">
<div class="adev-footer-columns">
<div>
<h2>Social Media</h2>
<ul>
<li *ngFor="let link of links.socialMedia | keyvalue">
<a [href]="link.value.href" [title]="link.value.title">{{ link.key | titlecase }}</a>
</li>
</ul>
</div>
<div>
<h2>Community</h2>
<ul>
<li *ngFor="let link of links.community | keyvalue">
<a [href]="link.value.href" [title]="link.value.title">{{ link.key | titlecase }}</a>
</li>
</ul>
</div>
<div>
<h2>Resources</h2>
<ul>
<li *ngFor="let link of links.resources | keyvalue">
<a
*ngIf="link.value.routerLink"
[routerLink]="link.value.routerLink"
[title]="link.value.title"
>{{ link.key | titlecase }}</a
>
<a *ngIf="link.value.href" [href]="link.value.href" [title]="link.value.title">{{
link.key | titlecase
}}</a>
</li>
</ul>
</div>
<div>
<h2>Languages</h2>
<ul>
<li *ngFor="let link of links.languages | keyvalue">
<a [href]="link.value.href" [title]="link.value.title">{{ link.key | titlecase }}</a>
</li>
</ul>
</div>
</div>
<p class="docs-license">
Super-powered by Google ©2010-2024. Code licensed under an
<a routerLink="/license" title="License text">MIT-style License</a>. Documentation licensed under
<a href="https://creativecommons.org/licenses/by/4.0/">CC BY 4.0</a>.
</p>
</div>
```
**footer.component.ts**
```
readonly links = {
socialMedia: {
blog: { href: 'MEDIUM', title: 'Angular blog' },
x: { href: 'X', title: 'X (formerly Twitter)' },
youtube: { href: 'YOUTUBE', title: 'YouTube' },
discord: {
href: 'https://discord.gg/angular',
title: 'Join the discussions at Angular Community Discord server.',
},
github: { href: 'GITHUB', title: 'GitHub' },
stackOverflow: {
href: 'https://stackoverflow.com/questions/tagged/angular',
title:
'Stack Overflow: where the community answers your technical Angular questions.',
},
},
community: {
contribute: {
href: 'https://github.com/angular/angular/blob/main/CONTRIBUTING.md',
title: 'Contribute to Angular',
},
codeOfConduct: {
href: 'https://github.com/angular/code-of-conduct/blob/main/CODE_OF_CONDUCT.md',
title: 'Treating each other with respect.',
},
reportIssues: {
href: 'https://github.com/angular/angular/issues',
title: 'Post issues and suggestions on github.',
},
devLibrary: {
href: 'https://devlibrary.withgoogle.com/products/angular?sort=updated',
title: "Google's DevLibrary",
},
experts: {
href: 'https://developers.google.com/community/experts/directory?specialization=angular',
title: 'Angular Google Developer Experts',
},
},
resources: {
pressKit: {
routerLink: '/press-kit',
title: 'Press contacts, logos, and branding.',
},
roadmap: { routerLink: '/roadmap', title: 'Roadmap' },
},
languages: {
chineseSimplified: {
href: 'https://angular.cn/',
title: '简体中文版',
},
chineseTraditional: {
href: 'https://angular.tw/',
title: '正體中文版',
},
japanese: { href: 'https://angular.jp/', title: '日本語版' },
korean: { href: 'https://angular.kr/', title: '한국어' },
greek: {
href: 'https://angular-gr.web.app',
title: 'Ελληνικά',
},
},
};
```
### Alternatives considered
- | help wanted,good first issue,area: docs-infra | low | Major |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.