attention-kernels

attention-kernels is a standalone package with the paged attention and cache reshape kernels from vLLM, with modifications for TGI.

Release files for attention-kernels 0.2.0.post2

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution for attention-kernels 0.2.0.post2
File	Size	Uploaded
attention_kernels-0.2.0.post2.tar.gz	53.3 kB	Jan 24, 2025	Details

Download URL	attention_kernels-0.2.0.post2.tar.gz
Size	53.3 kB
Tags	Source
SHA-256 checksum How to use checksums	`876024d93b0312b9792c0c0b0678eee2b814b6d4c48b1c1c5ce2b4651a827235`
BLAKE2b-256 checksum How to use checksums	`b379a4f57e0a5b8eaeef4701d8f599956ffe45a953e703d98cd563880fa49c46`
Upload date	Jan 24, 2025
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/5.1.1 CPython/3.12.8`