Alexander Matveev e02ac55617 [Performance] Optimize e2e overheads: Reduce python allocations (#7162)

2024-08-08 21:34:28 -07:00

..

__init__.py

[Core] Refactor Attention Take 2 (#3462)

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

abstract.py

[Misc] Support attention logits soft-capping with flash-attn (#7022)

2024-08-01 13:14:37 -07:00

blocksparse_attn.py

[Misc] Support attention logits soft-capping with flash-attn (#7022)

2024-08-01 13:14:37 -07:00

flash_attn.py

[Performance] Optimize e2e overheads: Reduce python allocations (#7162)

2024-08-08 21:34:28 -07:00

flashinfer.py

[Kernel] Fix Flashinfer Correctness (#7284)

2024-08-07 16:26:52 -07:00

ipex_attn.py

[Misc] Support attention logits soft-capping with flash-attn (#7022)

2024-08-01 13:14:37 -07:00

openvino.py

[Hardware][Intel] OpenVINO vLLM backend (#5379)

2024-06-28 13:50:16 +00:00

pallas.py

[Misc] Support attention logits soft-capping with flash-attn (#7022)

2024-08-01 13:14:37 -07:00

rocm_flash_attn.py

[Misc] Support attention logits soft-capping with flash-attn (#7022)

2024-08-01 13:14:37 -07:00

torch_sdpa.py

[Misc] Support attention logits soft-capping with flash-attn (#7022)

2024-08-01 13:14:37 -07:00

utils.py

[Performance] Optimize e2e overheads: Reduce python allocations (#7162)

2024-08-08 21:34:28 -07:00

xformers.py

[Misc] Support attention logits soft-capping with flash-attn (#7022)

2024-08-01 13:14:37 -07:00