Hongxia Yang 269d901734

[Bugfix][ROCm] fix the power of 2 exception from triton_unified_attention.py when running llama4 models and unit test fix (#18100) ...

Signed-off-by: Hongxia Yang <hongxia.yang@amd.com>
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
Co-authored-by: tjtanaa <tunjian.tan@embeddedllm.com>

2025-05-29 07:21:46 +08:00

..

conftest.py

Categorize tests/kernels/ based on kernel type (#16799)

2025-04-23 09:21:07 -04:00

test_attention_selector.py

fix broken test vllm:test_kernels - test_attention_selector.py::test_flash_attn (#17873)

2025-05-10 10:46:54 +08:00

test_attention.py

[ROCm][Kernel][V1] Enable AMD Radeon GPU Custom Paged Attention on v1 (#17004)

2025-05-21 08:35:00 -07:00

test_blocksparse_attention.py

Categorize tests/kernels/ based on kernel type (#16799)

2025-04-23 09:21:07 -04:00

test_cache.py

Allocate kv_cache with stride order (#16605)

2025-04-25 22:03:31 -07:00

test_cascade_flash_attn.py

Categorize tests/kernels/ based on kernel type (#16799)

2025-04-23 09:21:07 -04:00

test_encoder_decoder_attn.py

Categorize tests/kernels/ based on kernel type (#16799)

2025-04-23 09:21:07 -04:00

test_flash_attn.py

Update test_flash_attn.py (#17102)

2025-04-26 22:17:35 +00:00

test_flashinfer.py

Categorize tests/kernels/ based on kernel type (#16799)

2025-04-23 09:21:07 -04:00

test_flashmla.py

[Bugfix] Fix triton import with local TritonPlaceholder (#17446)

2025-05-06 17:53:09 +08:00

test_lightning_attn.py

Categorize tests/kernels/ based on kernel type (#16799)

2025-04-23 09:21:07 -04:00

test_merge_attn_states.py

Categorize tests/kernels/ based on kernel type (#16799)

2025-04-23 09:21:07 -04:00

test_mha_attn.py

Categorize tests/kernels/ based on kernel type (#16799)

2025-04-23 09:21:07 -04:00

test_mla_decode_cpu.py

Categorize tests/kernels/ based on kernel type (#16799)

2025-04-23 09:21:07 -04:00

test_prefix_prefill.py

Categorize tests/kernels/ based on kernel type (#16799)

2025-04-23 09:21:07 -04:00

test_rocm_attention_selector.py

[FEAT][ROCm]: Support AITER MLA on V1 Engine (#17523)

2025-05-09 10:42:05 +08:00

test_triton_decode_attention.py

Categorize tests/kernels/ based on kernel type (#16799)

2025-04-23 09:21:07 -04:00

test_triton_unified_attention.py

[Bugfix][ROCm] fix the power of 2 exception from triton_unified_attention.py when running llama4 models and unit test fix (#18100)

2025-05-29 07:21:46 +08:00