Hugging Face's logo

RedHatAI
/
quantization

kernel
Model card Files Community
1
quantization

Commit History

Build (aarch64-linux)
150f8c2

danieldk HF Staff commited on

Build (x86_64-linux)
daf6c87

danieldk HF Staff commited on

Prepare for Torch 2.8
eabe7c2

danieldk HF Staff commited on

Build (x86_64)
b65f8ab

danieldk HF Staff commited on

Build (aarch64)
4dcf20d

danieldk HF Staff commited on

Fix undefined symbol on CUDA 11.8
3313895

danieldk HF Staff commited on

Fix absolute imports
c516610

danieldk HF Staff commited on

Build (aarch64)
229f047

danieldk HF Staff commited on

Build (x86_64)
82ffd1f

danieldk HF Staff commited on

Update kernel builder flake
dfa7d18

danieldk HF Staff commited on

Export Marlin and quantization utilities
2f56f34

danieldk HF Staff commited on

Fixup platform FP8 data type query
a965094

danieldk HF Staff commited on

Build (AArch64)
a02ac19

danieldk HF Staff commited on

Set CUDA minimum versions for hopper/blackwell cutlass kernels
3370704

danieldk HF Staff commited on

Build (x86_64)
c73c09e

danieldk HF Staff commited on

Temporarily disable ROCm
d5fd23d

danieldk HF Staff commited on

Sync to vLLM 20250627
8aa00a3

danieldk HF Staff commited on

Sync on vLLM 20240402
d26f884

danieldk HF Staff commited on

Build (aarch64)
34013ad

danieldk HF Staff commited on

Build
cfc95fb

danieldk HF Staff commited on

Update flake
0435ccb

danieldk HF Staff commited on

Sync capabilities with upstream
59b2fef

danieldk HF Staff commited on

Build
32721c3

danieldk HF Staff commited on

Add support for ROCm
3c8bb73

danieldk HF Staff commited on

Add `flake.lock`
6d36a16

danieldk HF Staff commited on

Update for latest kernel-builder (add revision)
2e9b7c5

danieldk HF Staff commited on

Update for build.toml changes
116e562

danieldk HF Staff commited on

Build (Torch 2.6)
95272c7

danieldk HF Staff commited on

Build
329999a

danieldk HF Staff commited on

Export `ScalarType`/`scalartypes`
b2e431d

danieldk HF Staff commited on

Update flake.lock
613a874

danieldk HF Staff commited on

Build
d636d53

danieldk HF Staff commited on

Sync with vLLM
0da5bf5

danieldk HF Staff commited on

Build
0bc428e

danieldk HF Staff commited on

Adjust for latest kernel-builder changes
f44baaa

danieldk HF Staff commited on

Build
2e44e8c

danieldk HF Staff commited on

Simplify `flake.nix`
88883b3

danieldk HF Staff commited on

Build
d62ac09

danieldk HF Staff commited on

Expose ops (handy for tests etc.)
e3a7455

danieldk HF Staff commited on

Add a `flake.nix` for convenience
be218ea

danieldk HF Staff commited on

Build
a6c77d7

danieldk HF Staff commited on

Add full Marlin support and tests for Marlin/CUTLASS
165b25c

danieldk HF Staff commited on

Import CUTLASS tests and add missing scaled mm with zp signature
2dd62c9

danieldk HF Staff commited on

Add missing `scalar_type.hpp`
9d045c3

danieldk HF Staff commited on

Build
439141b

danieldk HF Staff commited on

Add GPTQ-Marlin
c31b5ce

danieldk HF Staff commited on

Build
c5018b2

danieldk HF Staff commited on

Add `scaled_(int|fp8)_quant` and `fp8_marlin_gemm`
5c6fb68

danieldk HF Staff commited on

Build
a77838d

danieldk HF Staff commited on