Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
kernels-community
/
paged-attention
like
1
Follow
kernels-community
42
kernel
License:
apache-2.0
Model card
Files
Files and versions
Community
1
main
paged-attention
Ctrl+K
Ctrl+K
4 contributors
History:
18 commits
drbh
HF Staff
feat: add tag for hfjob build
a0903d3
verified
18 days ago
build
Build
about 1 month ago
cuda-utils
Port vLLM attention kernels
4 months ago
paged-attention
Port vLLM attention kernels
4 months ago
tests
Rename to paged-attention
4 months ago
torch-ext
Update for build.toml changes
3 months ago
.gitattributes
Safe
1.56 kB
Port vLLM attention kernels
4 months ago
README.md
217 Bytes
feat: add tag for hfjob build
18 days ago
build.toml
1.13 kB
Use default CUDA capabilities
about 1 month ago
flake.lock
Safe
3.03 kB
Update flake inputs
about 1 month ago
flake.nix
Safe
332 Bytes
Fix flake input
about 1 month ago