wassname/vllm
1
0
Fork 0
mirror of https://github.com/wassname/vllm.git synced 2026-08-01 13:00:39 +08:00
Code Issues Packages Projects Releases Wiki Activity
1,949 Commits 1 Branch 0 Tags
7f62077af5159c625fe3ad1c812e6c1a2b93ba3b
Commit Graph
3 Commits
Author SHA1 Message Date
Michael GoinandGitHub 978aed5300 [Kernel][Attention] Separate Attention.kv_scale into k_scale and v_scale (#6081) 2024-07-16 15:31:32 -07:00
Roger WangandGitHub bd620b01fb [Kernel][CPU] Add Quick gelu to CPU (#5717) 2024-06-21 06:39:40 +00:00
bnellnmandGitHub 5467ac3196 [Kernel][Misc] Use TORCH_LIBRARY instead of PYBIND11_MODULE for custom ops (#5047) 2024-06-09 16:23:30 -04:00