Pleaplusone 77e10c9cab

[Perf][Deepseek] optimize gather_and_maybe_dequant_cache kernel's perf for extremely long sequence (#28029) ...

Signed-off-by: ganyi <ygan@amd.com>

2025-11-24 19:05:46 -07:00

..

conftest.py

…

test_aiter_flash_attn.py

…

test_attention_selector.py

…

test_attention.py

…

test_cache.py

[Perf][Deepseek] optimize gather_and_maybe_dequant_cache kernel's perf for extremely long sequence (#28029)

2025-11-24 19:05:46 -07:00

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

…

test_mha_attn.py

…

test_mla_decode_cpu.py

…

test_pack_unpack_triton.py

…

test_prefix_prefill.py

…

test_rocm_attention_selector.py

…

test_triton_decode_attention.py

…

test_triton_unified_attention.py

…