wassname/vllm
1
0
Fork 0
mirror of https://github.com/wassname/vllm.git synced 2026-07-31 12:50:41 +08:00
Code Issues Packages Projects Releases Wiki Activity
116 Commits 1 Branch 0 Tags
e548c1488ae1e93b5ca60359f4b292d2bee0b60d
Commit Graph
10 Commits
Author SHA1 Message Date
Zhuohan LiandGitHub 27f1410d06 New weight loader without np copy (#52) 2023-05-03 15:32:04 +08:00
Zhuohan LiandGitHub 4858f3bb45 Add an option to launch cacheflow without ray (#51) 2023-04-30 15:42:17 +08:00
Woosuk KwonandGitHub 0f4b32199e Support various block sizes & Change default block size to 16 (#38) 2023-04-15 09:03:24 -07:00
Woosuk KwonandGitHub 84eee24e20 Collect system stats in scheduler & Add scripts for experiments (#30) 2023-04-12 15:03:49 -07:00
Siyuan (Ryans) ZhuangandGitHub e3cec88aa5 Memcpy kernel for flash attention (#29) 
* optimize

* add benchmark

* add assert

* add test
 2023-04-10 18:22:49 -07:00
Woosuk KwonandGitHub ee88a7e5f3 Add an option to use dummy model weights (#33) 2023-04-08 23:36:12 -07:00
Woosuk KwonandGitHub c267b1a02c Add query stride to multi_query_cached_kv_attention & Add kernel benchmark script (#27) 
* Add query stride to multi_query_cached_kv_attention

* Add kernel benchmark script
 2023-04-08 13:36:09 -07:00
Woosuk KwonandGitHub 0f40557af6 Implement block copy kernel to optimize beam search (#32) 2023-04-07 17:45:07 -07:00
Woosuk KwonandGitHub 12659a0bd7 Add CUDA graph-based all reduce launcher (#26) 2023-04-05 11:16:57 -07:00
Zhuohan LiandGitHub c45f3c3ab6 Optimize tensor parallel execution speed (#17) 2023-04-01 00:51:08 +08:00