Tuukka Sarviandlarryli2-amd e34685dfc0 [ROCm][DSv4] Enable DSpark adaptive verification (#52362) ...

Signed-off-by: Tuukka Sarvi <tuukka.sarvi@amd.com>
Signed-off-by: larryli2-amd <larryli2@amd.com>
Co-authored-by: larryli2-amd <larryli2@amd.com>

2026-09-21 10:03:41 -05:00

..

mla

[ROCm][DSv4] Enable DSpark adaptive verification (#52362)

2026-09-21 10:03:41 -05:00

__init__.py

[V1] Implement vLLM V1 [1/N] (#9289)

2024-10-22 01:24:07 -07:00

b12x.py

[Kernel] Add B12X causal paged attention backend (#52017)

2026-09-01 10:42:02 -04:00

composite.py

[Attention] Add Triton/FlashInfer composite for multimodal prefix attention (#56305)

2026-09-13 14:29:41 +00:00

cpu_attn.py

[CPU][Perf] refactor paged attention for Arm CPUs (#56045)

2026-09-20 12:25:13 +08:00

fa_utils.py

Add pydocstyle to the ruff rules (#52136)

2026-09-16 16:44:29 +00:00

flash_attn_diffkv.py

Add pydocstyle to the ruff rules (#52136)

2026-09-16 16:44:29 +00:00

flash_attn.py

Add pydocstyle to the ruff rules (#52136)

2026-09-16 16:44:29 +00:00

flashinfer.py

[CI] Ignore ruff D209, rejoin the docstrings it split, and silence incompatible-rule warnings (#57212)

2026-09-16 10:57:24 -07:00

flex_attention.py

Add pydocstyle to the ruff rules (#52136)

2026-09-16 16:44:29 +00:00

gdn_attn.py

Add pydocstyle to the ruff rules (#52136)

2026-09-16 16:44:29 +00:00

hpc_attn.py

[Perf] Ensure async h2d copies are pinned in more places (#55202)

2026-09-04 17:17:01 -07:00

linear_attn.py

[Attention]: Use KVCacheSpec for AttentionMetadataBuilder type hints (#50148)

2026-07-31 11:20:18 +00:00

mamba1_attn.py

[HMA]Fix corner case when hybrid page_size can not be evenly divided issue (blk_size=64,tp=4) (#37467)

2026-03-30 16:47:30 +00:00

mamba2_attn.py

Add pydocstyle to the ruff rules (#52136)

2026-09-16 16:44:29 +00:00

mamba_attn.py

Add pydocstyle to the ruff rules (#52136)

2026-09-16 16:44:29 +00:00

recoverssm_metadata.py

[K3] support recoverssm for K3 (#51855)

2026-08-17 19:34:14 +08:00

registry.py

Add pydocstyle to the ruff rules (#52136)

2026-09-16 16:44:29 +00:00

rocm_aiter_fa.py

[ROCm][Bugfix] Ignore descales for unquantized AITER caches (#56726)

2026-09-17 01:29:50 +00:00

rocm_aiter_unified_attn.py

[CI] Ignore ruff D209, rejoin the docstrings it split, and silence incompatible-rule warnings (#57212)

2026-09-16 10:57:24 -07:00

rocm_attn.py

[CI] Ignore ruff D209, rejoin the docstrings it split, and silence incompatible-rule warnings (#57212)

2026-09-16 10:57:24 -07:00

short_conv_attn.py

[Perf][GDN] Build cudagraph-capture metadata without a device sync (#55404)

2026-09-04 17:40:17 -07:00

triton_attn_diffkv.py

[6/N][KV-Cache Layout Refactor] Standardize KV cache layout (#51718)

2026-08-21 17:47:49 -07:00

triton_attn.py

[CI] Ignore ruff D209, rejoin the docstrings it split, and silence incompatible-rule warnings (#57212)

2026-09-16 10:57:24 -07:00

triton_flash_attn.py

[Attention] Add Triton/FlashInfer composite for multimodal prefix attention (#56305)

2026-09-13 14:29:41 +00:00

triton_flashinfer.py

[Attention] Add Triton/FlashInfer composite for multimodal prefix attention (#56305)

2026-09-13 14:29:41 +00:00

turboquant_attn.py

[6/N][KV-Cache Layout Refactor] Standardize KV cache layout (#51718)

2026-08-21 17:47:49 -07:00

utils.py

Add pydocstyle to the ruff rules (#52136)

2026-09-16 16:44:29 +00:00