Go to file
2023-03-01 21:13:08 -08:00
cacheflow Use FlashAttention for multi_query_kv_attention (#4) 2023-03-01 21:13:08 -08:00
csrc Implement single_query_cached_kv_attention kernel (#3) 2023-03-01 15:02:19 -08:00
tests/kernels Use FlashAttention for multi_query_kv_attention (#4) 2023-03-01 21:13:08 -08:00
.gitignore Add gitignore 2023-02-16 07:47:21 +00:00
README.md Use FlashAttention for multi_query_kv_attention (#4) 2023-03-01 21:13:08 -08:00
server.py Use FlashAttention for multi_query_kv_attention (#4) 2023-03-01 21:13:08 -08:00
setup.py Implement single_query_cached_kv_attention kernel (#3) 2023-03-01 15:02:19 -08:00

CacheFlow

Installation

pip install cmake torch transformers
pip install flash-attn # This may take up to 10 mins.
pip install -e .

Run

python server.py