wassname/vllm
1
0
Fork 0
mirror of https://github.com/wassname/vllm.git synced 2026-08-09 12:30:26 +08:00
Code Issues Packages Projects Releases Wiki Activity
477 Commits 1 Branch 0 Tags
06e9ebebd51c3db779dedec5556251c8ecc3a00a
Commit Graph
7 Commits
Author SHA1 Message Date
ljssandGitHub e1054247ba [Optimization] Implement fused add rmsnorm (#1667) 2023-11-18 18:18:02 -08:00
Woosuk KwonandGitHub c1376e0f82 Change scheduler & input tensor shape (#1381) 2023-10-16 17:48:42 -07:00
Woosuk KwonandGitHub 8ce9c50d40 Avoid compiling kernels for double data type (#933) 2023-09-02 14:59:47 +09:00
Woosuk KwonandGitHub 0b98ba15c7 Change the name to vLLM (#150) 2023-06-17 03:07:40 -07:00
Woosuk KwonandGitHub e070829ae8 Support bfloat16 data type (#54) 2023-05-03 14:09:44 -07:00
Woosuk KwonandGitHub 436e523bf1 Refactor attention kernels (#53) 2023-05-03 13:40:13 -07:00
Woosuk KwonandGitHub 09e9245478 Add custom kernel for RMS normalization (#16) 2023-04-01 00:51:22 +08:00