Woosuk Kwon 89579a201f

[Misc] Use vllm-flash-attn instead of flash-attn (#4686)

2024-05-08 13:15:34 -07:00

..

__init__.py

[Core] Refactor Attention Take 2 (#3462)

2024-03-25 04:39:33 +00:00

abstract.py

[Core][Optimization] change python dict to pytorch tensor for blocks to swap (#4659)

2024-05-08 12:07:05 -07:00

flash_attn.py

[Misc] Use vllm-flash-attn instead of flash-attn (#4686)

2024-05-08 13:15:34 -07:00

flashinfer.py

[Misc] Use vllm-flash-attn instead of flash-attn (#4686)

2024-05-08 13:15:34 -07:00

rocm_flash_attn.py

[Core][Optimization] change python dict to pytorch tensor for blocks to swap (#4659)

2024-05-08 12:07:05 -07:00

torch_sdpa.py

[Core][Optimization] change python dict to pytorch tensor for blocks to swap (#4659)

2024-05-08 12:07:05 -07:00

xformers.py

[Misc] Add get_name method to attention backends (#4685)

2024-05-08 09:59:31 -07:00