wassname/vllm
1
0
Fork 0
mirror of https://github.com/wassname/vllm.git synced 2026-07-19 11:29:39 +08:00
Code Issues Packages Projects Releases Wiki Activity
98 Commits 1 Branch 0 Tags
897cb2ae28e93de1b22ecfbffcccfb9493f8f4d9
Commit Graph
13 Commits
Author SHA1 Message Date
Woosuk KwonandGitHub 897cb2ae28 Optimize data movement (#20) 2023-04-02 00:30:17 -07:00
Woosuk KwonandGitHub 88c0268a18 Implement custom kernel for LLaMA rotary embedding (#14) 2023-03-30 11:04:21 -07:00
Zhuohan LiandGitHub 2f49f15585 Support tensor parallel (#2) 2023-03-21 13:45:42 -07:00
Woosuk KwonandGitHub cfae35b861 Add miscellaneous updates (#8) 2023-03-13 13:48:38 -07:00
Woosuk KwonandGitHub 04e5acc08e Fix a bug in 1D input shape (#5) 2023-03-06 10:05:27 -08:00
Woosuk KwonandGitHub 3e9f991d6a Use FlashAttention for multi_query_kv_attention (#4) 2023-03-01 21:13:08 -08:00
Woosuk KwonandGitHub 0deacbce6e Implement single_query_cached_kv_attention kernel (#3) 2023-03-01 15:02:19 -08:00
Woosuk Kwon 762fd1c3fa Refactor and annotate types for attention 2023-02-24 08:58:46 +00:00
Woosuk Kwon 7f22f90e8c Remove xformers 2023-02-24 08:36:16 +00:00
Woosuk Kwon 932844f1cd Fix attention 2023-02-23 23:02:25 +00:00
Woosuk Kwon ba84b8728a Fix attention 2023-02-23 22:29:46 +00:00
Woosuk Kwon 87e0bcd426 Fix attention 2023-02-23 21:32:02 +00:00
Woosuk Kwon d4bc1a4d24 Add unoptimized OPT Attention 2023-02-23 09:31:55 +00:00