Matthew Bonanni 77a73458e3 Reapply [Attention] Refactor check_and_update_config (#35122) ...

Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>

2026-03-09 07:17:14 -07:00

..

conftest.py

…

test_aiter_flash_attn.py

…

test_attention_selector.py

Reapply [Attention] Refactor check_and_update_config (#35122)

2026-03-09 07:17:14 -07:00

test_attention.py

[Bugfix][CI] fix typos (#34934)

2026-03-05 17:05:46 +00:00

test_cache.py

…

test_cascade_flash_attn.py

…

test_cpu_attn.py

…

test_cutlass_mla_decode.py

…

test_deepgemm_attention.py

…

test_flash_attn.py

…

test_flashinfer_mla_decode.py

…

test_flashinfer_trtllm_attention.py

…

test_flashinfer.py

…

test_flashmla_sparse.py

…

test_flashmla.py

…

test_lightning_attn.py

…

test_merge_attn_states.py

[Hardware] Replace torch.cuda.synchronize() api with torch.accelerator.synchronize (#36085)

2026-03-05 10:36:39 +00:00

test_mha_attn.py

[MM Encoder] Default to use TORCH_SDPA backend for ViT on Volta/Turing GPU (#36472)

2026-03-09 03:43:44 -07:00

test_mla_decode_cpu.py

…

test_pack_unpack_triton.py

…

test_prefix_prefill.py

[Hardware] Replace torch.cuda.synchronize() api with torch.accelerator.synchronize (#36085)

2026-03-05 10:36:39 +00:00

test_rocm_attention_selector.py

…

test_triton_decode_attention.py

…

test_triton_prefill_attention.py

…

test_triton_unified_attention.py

…

test_use_trtllm_attention.py

TRTLLM gen-full attn Test Coverage (#34986)

2026-03-03 11:35:34 -05:00