vllm/benchmark
Siyuan (Ryans) Zhuang e3cec88aa5
Memcpy kernel for flash attention (#29)
* optimize

* add benchmark

* add assert

* add test
2023-04-10 18:22:49 -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_cache.py Memcpy kernel for flash attention (#29) 2023-04-10 18:22:49 -07:00
benchmark_latency.py Add an option to use dummy model weights (#33) 2023-04-08 23:36:12 -07:00