wassname/vllm
1
0
Fork 0
mirror of https://github.com/wassname/vllm.git synced 2026-06-30 11:10:43 +08:00
Code Issues Packages Projects Releases Wiki Activity
2,681 Commits 1 Branch 0 Tags
1009e93c5d634c724eeff3d4e453369337f502d4
Commit Graph

3 Commits

Author SHA1 Message Date
sroy745 1009e93c5d [Encoder decoder] Add cuda graph support during decoding for encoder-decoder models (#7631) 2024-09-17 07:35:01 -07:00
SangBin Cho ff7ec82c4d [Core] Optimize SPMD architecture with delta + serialization optimization (#7109) 2024-08-18 17:57:20 -07:00
afeldman-nm 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