Woosuk KwonandGitHub 3e9f991d6a Use FlashAttention for multi_query_kv_attention (#4)

2023-03-01 21:13:08 -08:00

..

attention.py

Use FlashAttention for multi_query_kv_attention (#4)

2023-03-01 21:13:08 -08:00

cache.py

Implement single_query_cached_kv_attention kernel (#3)

2023-03-01 15:02:19 -08:00