Woosuk Kwon c267b1a02c Add query stride to multi_query_cached_kv_attention & Add kernel benchmark script (#27) ...

* Add query stride to multi_query_cached_kv_attention

* Add kernel benchmark script

2023-04-08 13:36:09 -07:00

..

benchmark_attention.py

Add query stride to multi_query_cached_kv_attention & Add kernel benchmark script (#27)

2023-04-08 13:36:09 -07:00

benchmark_latency.py

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

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