Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
kernels-community
/
quantization
like
1
Follow
kernels-community
42
kernel
License:
apache-2.0
Model card
Files
Files and versions
Community
1
c31b5ce
quantization
Ctrl+K
Ctrl+K
3 contributors
History:
7 commits
danieldk
HF Staff
Add GPTQ-Marlin
c31b5ce
5 months ago
build
Build
6 months ago
compressed_tensors
Add `scaled_(int|fp8)_quant` and `fp8_marlin_gemm`
6 months ago
core
Add `scaled_(int|fp8)_quant` and `fp8_marlin_gemm`
6 months ago
cutlass_extensions
Add cutlass_w8a8
6 months ago
cutlass_w8a8
Add cutlass_w8a8
6 months ago
ext-torch
Add GPTQ-Marlin
5 months ago
fp8
Add `scaled_(int|fp8)_quant` and `fp8_marlin_gemm`
6 months ago
gptq_marlin
Add GPTQ-Marlin
5 months ago
.gitattributes
Safe
1.56 kB
Build
6 months ago
LICENSE
Safe
11.4 kB
Add cutlass_w8a8
6 months ago
README.md
Safe
181 Bytes
Fixup metadata
6 months ago
build.toml
2.13 kB
Add GPTQ-Marlin
5 months ago
dispatch_utils.h
Safe
1.49 kB
Add `scaled_(int|fp8)_quant` and `fp8_marlin_gemm`
6 months ago
