https://github.com/danieldk/attention-kernels

Attention kernels
https://github.com/danieldk/attention-kernels

Last synced: 10 months ago
JSON representation

Attention kernels

• Host: GitHub
• URL: https://github.com/danieldk/attention-kernels
• Owner: danieldk
• License: apache-2.0
• Created: 2024-11-15T10:31:40.000Z (about 1 year ago)
• Default Branch: main
• Last Pushed: 2025-01-29T13:30:50.000Z (11 months ago)
• Last Synced: 2025-01-29T14:30:24.521Z (11 months ago)
• Language: Cuda
• Size: 82 KB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

          
## attention-kernels

`attention-kernels` is a standalone package with the paged attention and

cache reshape kernels from [vLLM](https://github.com/vllm-project/vllm), with modifications for TGI.