wassname/vllm
1
0
Fork 0
mirror of https://github.com/wassname/vllm.git synced 2026-07-22 13:00:10 +08:00
Code Issues Packages Projects Releases Wiki Activity
2,955 Commits 1 Branch 0 Tags
21efb603f5f88a0d78ad11e4fbc6e18fe83916d4
Commit Graph
3 Commits
Author SHA1 Message Date
youkaichaoandGitHub a9b15c606f [torch.compile] use empty tensor instead of None for profiling (#8875) 2024-09-27 08:11:32 -07:00
afeldman-nmGitHubAndrew FeldmanNick Hill
 		fd95e026e0 [Core] Subclass ModelRunner to support cross-attention & encoder sequences (towards eventual encoder/decoder model support) (#4942) 
Co-authored-by: Andrew Feldman <afeld2012@gmail.com>
Co-authored-by: Nick Hill <nickhill@us.ibm.com>
 2024-08-06 16:51:47 -04:00
afeldman-nmGitHubWoosuk Kwon
 		543aa48573 [Kernel] Correctly invoke prefill & decode kernels for cross-attention (towards eventual encoder/decoder model support) (#4888) 
Co-authored-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
 2024-07-08 17:12:15 +00:00