Qiuandgemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com> 968060c15a [bugfix] correct local_chunk_len for DCP in reorg_kvcache with long context (#28526) ...

Signed-off-by: QiuChunshuo <qiuchunshuo@huawei.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>

2025-11-13 11:29:22 -08:00

..

__init__.py

[Attention] MLA support for V1 (#13789)

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

common.py

[bugfix] correct local_chunk_len for DCP in reorg_kvcache with long context (#28526)

2025-11-13 11:29:22 -08:00

cutlass_mla.py

[Perf] Refactor cudagraph_support to enable full CUDA graphs for spec decoding with FlashInfer (#28479)

2025-11-13 01:56:40 +09:00

flashattn_mla.py

[Perf] Refactor cudagraph_support to enable full CUDA graphs for spec decoding with FlashInfer (#28479)

2025-11-13 01:56:40 +09:00

flashinfer_mla.py

[Perf] Refactor cudagraph_support to enable full CUDA graphs for spec decoding with FlashInfer (#28479)

2025-11-13 01:56:40 +09:00

flashmla_sparse.py

[CI Failure] Fix backend selection for encoder-only models (#28534)

2025-11-13 10:11:27 -05:00

flashmla.py

[Perf] Refactor cudagraph_support to enable full CUDA graphs for spec decoding with FlashInfer (#28479)

2025-11-13 01:56:40 +09:00

indexer.py

[Perf] Refactor cudagraph_support to enable full CUDA graphs for spec decoding with FlashInfer (#28479)

2025-11-13 01:56:40 +09:00

rocm_aiter_mla.py

[Perf] Refactor cudagraph_support to enable full CUDA graphs for spec decoding with FlashInfer (#28479)

2025-11-13 01:56:40 +09:00

triton_mla.py

VLLM_USE_TRITON_FLASH_ATTN V0 variable deprecation (#27611)

2025-11-11 18:34:36 -08:00