wassname/vllm
1
0
Fork 0
mirror of https://github.com/wassname/vllm.git synced 2026-07-18 12:50:17 +08:00
Code Issues Packages Projects Releases Wiki Activity
1,627 Commits 1 Branch 0 Tags
a3e8a05d4c1b79dd44eb92bb6f57eb40c3fbdb21
Commit Graph
4 Commits
Author SHA1 Message Date
Cyrus LeungandGitHub 0e9164b40a [mypy] Enable type checking for test directory (#5017) 2024-06-15 04:45:31 +00:00
Philipp MoritzandGitHub 51a08e7d8f [Kernel] Re-tune Mixtral MoE configurations for FP8 on H100 (#5238) 2024-06-05 10:59:14 -07:00
Woosuk KwonandGitHub 27208be66e [Kernel] Add back batch size 1536 and 3072 to MoE tuning (#5242) 2024-06-04 09:58:47 -07:00
Woosuk KwonandGitHub 3a434b07ed [Kernel] Enhance MoE benchmarking & tuning script (#4921) 2024-06-03 20:06:59 -07:00