Travis Johnson 0032903a5b [Bugfix] detect alibi and revert to FA2 (#15231) ...

Signed-off-by: Travis Johnson <tsjohnso@us.ibm.com>

2025-03-20 19:20:16 -07:00

..

mla

[Attention] Flash Attention 3 - fp8 (#14570)

2025-03-20 01:14:20 -04:00

__init__.py

[Core] Refactor Attention Take 2 (#3462)

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

abstract.py

[Attention] Flash Attention 3 - fp8 (#14570)

2025-03-20 01:14:20 -04:00

blocksparse_attn.py

fix some typos : supported_head_sizes (#14627)

2025-03-11 10:38:24 -07:00

flash_attn.py

[Bugfix] detect alibi and revert to FA2 (#15231)

2025-03-20 19:20:16 -07:00

flashinfer.py

[Misc] set single whitespace between log sentences (#13771)

2025-02-25 10:26:12 +08:00

flashmla.py

[V1][Bugfix] Standardize quantized kv cache rejection for attention backends (#14221)

2025-03-06 14:18:29 -08:00

hpu_attn.py

[V1][Bugfix] Standardize quantized kv cache rejection for attention backends (#14221)

2025-03-06 14:18:29 -08:00

ipex_attn.py

[V1][Bugfix] Standardize quantized kv cache rejection for attention backends (#14221)

2025-03-06 14:18:29 -08:00

openvino.py

[Bugfix] Fix OpenVINO model runner (#12750)

2025-02-04 22:42:46 -08:00

pallas.py

[V1][Bugfix] Standardize quantized kv cache rejection for attention backends (#14221)

2025-03-06 14:18:29 -08:00

placeholder_attn.py

[Model] IBM/NASA Prithvi Geospatial model (#12830)

2025-02-11 20:34:30 -08:00

rocm_flash_attn.py

[FEAT] [ROCm] [Embedding] Add encoder-only model support into ROCm Flash Attention to enable embedding models. (#14664)

2025-03-12 09:31:19 -07:00

torch_sdpa.py

[CPU] Support FP8 KV cache (#14741)

2025-03-14 22:07:36 -07:00

triton_mla.py

[V1][Bugfix] Standardize quantized kv cache rejection for attention backends (#14221)

2025-03-06 14:18:29 -08:00

utils.py

[Attention] Flash Attention 3 - fp8 (#14570)

2025-03-20 01:14:20 -04:00

xformers.py

[Bugfix][CI] ALiBi test case in xformers multi_query_kv_attention (#11301)

2025-03-05 20:00:53 -08:00