Kernels:
Trusted publisher
This is the repository card of kernels-community/paged-attention that has been pushed on the Hub. It was built to be used with the kernels library. This card was automatically generated.
How to use
# make sure `kernels` is installed: `pip install -U kernels`
from kernels import get_kernel
kernel_module = get_kernel("kernels-community/paged-attention", version=2)
_private_for_testing = kernel_module._private_for_testing
_private_for_testing(...)
Available functions
_private_for_testingconvert_fp8copy_blockspaged_attention_v1paged_attention_v2reshape_and_cachereshape_and_cache_flashswap_blocks
Benchmarks
Benchmarking script is available for this kernel. Run kernels benchmark kernels-community/paged-attention --version 2.
- Downloads last month
- 1,764
apache-2.0
Supported hardwares new
CUDA
ROCm
Metal
- Torch
- 2.14
- OS
- macoslinux
- Arch
- x86_64aarch64
- Kernel Builder
- a7f0afd










