xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-04-19 09:47:03 +08:00
Code Issues Packages Projects Releases Wiki Activity
vllm/vllm/attention
History
Juan Villamizar 6c0b04515f
[ROCm][Hardware][AMD] Use Triton Kernel for default FA on ROCm (#3643) 
Co-authored-by: jpvillam <jpvillam@amd.com>
Co-authored-by: Gregory Shtrasberg <Gregory.Shtrasberg@amd.com>
Co-authored-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
2024-04-09 15:10:47 -07:00
..
backends
[ROCm][Hardware][AMD] Use Triton Kernel for default FA on ROCm (#3643)
2024-04-09 15:10:47 -07:00
ops
[ROCm][Hardware][AMD] Use Triton Kernel for default FA on ROCm (#3643)
2024-04-09 15:10:47 -07:00
__init__.py
[CI] Try introducing isort. (#3495)
2024-03-25 07:59:47 -07:00
layer.py
Enable scaled FP8 (e4m3fn) KV cache on ROCm (AMD GPU) (#3290)
2024-04-03 14:15:55 -07:00
selector.py
[ROCm][Hardware][AMD] Use Triton Kernel for default FA on ROCm (#3643)
2024-04-09 15:10:47 -07:00