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

..

prefill

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

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

__init__.py

[Attention] MLA support for V1 (#13789)

2025-02-27 13:14:17 -05:00

aiter_triton_mla.py

[CI] Fix mypy for vllm/v1/structured_output (#32722)

2026-01-23 11:55:51 +08:00

amx_mla.py

[CPU] Add CPU FP8 W8A8 linear/MoE support (#49942)

2026-09-18 17:59:42 +08:00

compressor_utils.py

[Feat][Model] Support encoder-side SWA-bounded replay for DeepSeek-V4.1-Flash (#56227)

2026-09-18 15:01:24 -07:00

cpu_mla.py

[CPU] Add MLA backend so DeepSeek-V2/V3 can run on CPU (#49453)

2026-08-06 16:51:41 +08:00

cutlass_mla.py

[Attention] Require explicit DCP support from attention implementations (#55780)

2026-09-08 14:04:27 -07:00

flashattn_mla_sparse.py

[3/N] HiSparse: host-resident sparse-MLA decode hot-buffering (#53781)

2026-09-12 00:36:47 -04:00

flashattn_mla.py

[Attention] Require explicit DCP support from attention implementations (#55780)

2026-09-08 14:04:27 -07:00

flashinfer_mla_sparse_sm90.py

[Bugfix] Prevent out-of-bounds access in FlashInfer SM90 sparse MLA mixed batches (#56969)

2026-09-15 15:03:58 +00:00

flashinfer_mla_sparse_sm120.py

[3/N] HiSparse: host-resident sparse-MLA decode hot-buffering (#53781)

2026-09-12 00:36:47 -04:00

flashinfer_mla_sparse.py

[Bugfix][Attention] Stabilize sparse-MLA DCP for GLM PCP evals (#55879)

2026-09-15 09:58:30 -07:00

flashinfer_mla.py

[Attention] Require explicit DCP support from attention implementations (#55780)

2026-09-08 14:04:27 -07:00

flashmla_sparse.py

[Bugfix][MLA] Reserve sparse prefill buffers before KV cache sizing (#57575)

2026-09-18 21:22:18 +00:00

flashmla.py

[Attention] Require explicit DCP support from attention implementations (#55780)

2026-09-08 14:04:27 -07:00

index_group.py

[Bugfix][SparseMLA] Fix piecewise cudagraph capture crash in index group (#56825)

2026-09-15 06:51:35 +00:00

indexer.py

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

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

rocm_aiter_mla_sparse.py

[Bugfix][ROCm] Add record_logical_topk_ready to ROCMAiterMLASparseImpl (GLM-5.3-Flash boot crash) (#57252)

2026-09-17 22:34:56 +00:00

rocm_aiter_mla.py

Add pydocstyle to the ruff rules (#52136)

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

sparse_indexer.py

[DSA] Wire DeepGEMM sparse MQA logits into the DeepSeek V4.1 indexer (#56254)

2026-09-15 14:07:14 -07:00

sparse_swa.py

[Perf][Attention] Avoid redundant sparse attention metadata operations (#57885)

2026-09-21 00:08:43 -07:00

sparse_utils.py

Add pydocstyle to the ruff rules (#52136)

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

tokenspeed_mla.py

[Attention] Require explicit DCP support from attention implementations (#55780)

2026-09-08 14:04:27 -07:00

triton_mla.py

[Bugfix][MLA] TritonMLA: fix illegal memory access on causal multi-token decode (#51065)

2026-09-18 03:49:53 -05:00

xpu_mla_sparse.py

[Bugfix][MLA] Read sparse model settings from text config (#56160)

2026-09-11 18:02:13 +00:00