Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
kernels-community
/
quantization
like
2
Follow
kernels-community
94
kernel
License:
apache-2.0
Model card
Files
Files and versions
Community
1
85bad96
quantization
Ctrl+K
Ctrl+K
3 contributors
History:
38 commits
danieldk
HF Staff
Temporarily disable ROCm
85bad96
2 months ago
build
Build (aarch64)
2 months ago
compressed_tensors
Sync with vLLM
5 months ago
core
Sync with vLLM
5 months ago
cutlass_extensions
Sync with vLLM
5 months ago
cutlass_w8a8
Sync with vLLM
5 months ago
fp8
Sync with vLLM
5 months ago
gptq_marlin
Sync with vLLM
5 months ago
marlin
Add full Marlin support and tests for Marlin/CUTLASS
6 months ago
tests
Add full Marlin support and tests for Marlin/CUTLASS
6 months ago
torch-ext
Add support for ROCm
3 months ago
.gitattributes
1.56 kB
Build
7 months ago
LICENSE
11.4 kB
Add cutlass_w8a8
7 months ago
README.md
195 Bytes
Update README.md (#1)
4 months ago
build.toml
3.13 kB
Temporarily disable ROCm
2 months ago
dispatch_utils.h
1.49 kB
Add `scaled_(int|fp8)_quant` and `fp8_marlin_gemm`
7 months ago
flake.lock
3.03 kB
Update flake input
2 months ago
flake.nix
335 Bytes
Add support for ROCm
3 months ago
vectorization.cuh
778 Bytes
Sync with vLLM
5 months ago
