Woosuk KwonandGitHub c9d5b6d4a8 Replace FlashAttention with xformers (#70)

2023-05-05 02:01:08 -07:00

..

cache_engine.py

Implement block copy kernel to optimize beam search (#32)

2023-04-07 17:45:07 -07:00

controller.py

New weight loader without np copy (#52)

2023-05-03 15:32:04 +08:00

worker.py

Replace FlashAttention with xformers (#70)

2023-05-05 02:01:08 -07:00