Cyrus Leung 9fb52e523a

[V1] Support any head size for FlexAttention backend (#20467) ...

Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>

2025-07-06 09:54:36 -07:00

..

conftest.py

…

test_attention_selector.py

[V1] Support any head size for FlexAttention backend (#20467)

2025-07-06 09:54:36 -07:00

test_attention.py

test_attention compat with coming xformers change (#20487)

2025-07-05 19:37:59 -07:00

test_blocksparse_attention.py

…

test_cache.py

[CI] change spell checker from codespell to typos (#18711)

2025-06-11 19:57:10 -07:00

test_cascade_flash_attn.py

…

test_encoder_decoder_attn.py

[CI] change spell checker from codespell to typos (#18711)

2025-06-11 19:57:10 -07:00

test_flash_attn.py

…

test_flashinfer.py

…

test_flashmla.py

…

test_lightning_attn.py

…

test_merge_attn_states.py

…

test_mha_attn.py

…

test_mla_decode_cpu.py

[Refactor] Remove duplicate ceil_div (#20023)

2025-06-25 05:19:09 +00:00

test_prefix_prefill.py

…

test_rocm_attention_selector.py

[BugFix][V1][ROCm] Triton MLA uses V0 backend on V1 engine (#19067)

2025-07-01 16:12:19 +08:00

test_triton_decode_attention.py

[Refactor] Remove duplicate ceil_div (#20023)

2025-06-25 05:19:09 +00:00

test_triton_unified_attention.py

…