Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
kernels-community
/
quantization
like
3
Follow
kernels-community
116
kernel
License:
apache-2.0
Model card
Files
Files and versions
Community
1
d5fd23d
quantization
Ctrl+K
Ctrl+K
2 contributors
History:
38 commits
danieldk
HF Staff
Temporarily disable ROCm
d5fd23d
13 days ago
attention
Sync to vLLM 20250627
15 days ago
build
Build (aarch64)
3 months ago
compressed_tensors
Sync to vLLM 20250627
15 days ago
core
Sync to vLLM 20250627
15 days ago
cutlass_extensions
Sync to vLLM 20250627
15 days ago
cutlass_w8a8
Sync to vLLM 20250627
15 days ago
fp8
Sync to vLLM 20250627
15 days ago
gptq_marlin
Sync to vLLM 20250627
15 days ago
marlin
Sync to vLLM 20250627
15 days ago
tests
Sync to vLLM 20250627
15 days ago
torch-ext
Sync to vLLM 20250627
15 days ago
.gitattributes
Safe
1.56 kB
Build
7 months ago
LICENSE
Safe
11.4 kB
Add cutlass_w8a8
7 months ago
README.md
Safe
195 Bytes
Update README.md (#1)
5 months ago
build.toml
5.88 kB
Temporarily disable ROCm
13 days ago
cuda_utils.h
Safe
1.41 kB
Sync on vLLM 20240402
3 months ago
dispatch_utils.h
Safe
3.9 kB
Sync to vLLM 20250627
15 days ago
flake.lock
4.47 kB
Sync to vLLM 20250627
15 days ago
flake.nix
Safe
335 Bytes
Add support for ROCm
4 months ago
utils.cuh
Safe
1.84 kB
Sync on vLLM 20240402
3 months ago
vectorization.cuh
Safe
878 Bytes
Sync to vLLM 20250627
15 days ago
vectorization_utils.cuh
Safe
2.61 kB
Sync to vLLM 20250627
15 days ago