wassname/vllm
1
0
Fork 0
mirror of https://github.com/wassname/vllm.git synced 2026-06-30 04:37:36 +08:00
Code Issues Packages Projects Releases Wiki Activity
2,281 Commits 1 Branch 0 Tags
d2bc4510a42c3a1f00a68c4387d28fb1991f7dcb
Commit Graph

2 Commits

Author SHA1 Message Date
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
afeldman-nm 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