Attention kernels
Project description
attention-kernels
attention-kernels is a standalone package with the paged attention and
cache reshape kernels from vLLM, with modifications for TGI.
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
attention_kernels-0.1.0.tar.gz
(49.8 kB
view details)
File details
Details for the file attention_kernels-0.1.0.tar.gz.
File metadata
- Download URL: attention_kernels-0.1.0.tar.gz
- Upload date:
- Size: 49.8 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/5.1.1 CPython/3.12.7
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | 90c40acc4ce625ca293f28136194de5da6dc335c898a7adebda06d22db5bcc96 |
|
| MD5 | 3e0faa3af2e6b164e214ac5a1d4580f8 |
|
| BLAKE2b-256 | 1227ff9833e02e7c025fba2a48abe764080467a557b1b989ec34fd1924b590ec |
