ErkinSagiroglu 55137e8ee3

Fix: MI100 Support By Bypassing Custom Paged Attention (#9560)

2024-10-26 12:12:57 +00:00

..

__init__.py

[Core] Refactor Attention Take 2 (#3462)

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

abstract.py

Support BERTModel (first encoder-only embedding model) (#9056)

2024-10-17 23:21:01 +00:00

blocksparse_attn.py

[SpecDec] Remove Batch Expansion (2/3) (#9298)

2024-10-12 05:13:37 +00:00

flash_attn.py

[Doc] Consistent naming of attention backends (#9498)

2024-10-21 22:29:57 +08:00

flashinfer.py

[Doc] Consistent naming of attention backends (#9498)

2024-10-21 22:29:57 +08:00

ipex_attn.py

[Doc] Consistent naming of attention backends (#9498)

2024-10-21 22:29:57 +08:00

openvino.py

[Doc] Consistent naming of attention backends (#9498)

2024-10-21 22:29:57 +08:00

pallas.py

[Doc] Consistent naming of attention backends (#9498)

2024-10-21 22:29:57 +08:00

placeholder_attn.py

[Doc] Consistent naming of attention backends (#9498)

2024-10-21 22:29:57 +08:00

rocm_flash_attn.py

Fix: MI100 Support By Bypassing Custom Paged Attention (#9560)

2024-10-26 12:12:57 +00:00

torch_sdpa.py

[Hardware][CPU] using current_platform.is_cpu (#9536)

2024-10-22 00:50:43 -07:00

utils.py

[Doc] Consistent naming of attention backends (#9498)

2024-10-21 22:29:57 +08:00

xformers.py

[Doc] Consistent naming of attention backends (#9498)

2024-10-21 22:29:57 +08:00