grimulkan a1257fd1ea [Kernel] Add FP8 KV cache support to Triton MLA decode attention (#34597) ...

Signed-off-by: grimulkan <grimulkan@gmail.com>

2026-03-12 08:32:34 -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

cutlass_mla.py

[Platform] Add current_platform.num_compute_units interface (#35042)

2026-02-24 22:22:49 -08:00

flashattn_mla.py

Reapply [Attention] Refactor check_and_update_config (#35122)

2026-03-09 07:17:14 -07:00

flashinfer_mla_sparse.py

Reapply [Attention] Refactor check_and_update_config (#35122)

2026-03-09 07:17:14 -07:00

flashinfer_mla.py

Reapply [Attention] Refactor check_and_update_config (#35122)

2026-03-09 07:17:14 -07:00

flashmla_sparse.py

[Attention][Perf][Kernel] Replace torch.cat with vectorized CUDA kernel MLA query concat - DeepSeek-V3.2 (#34917)

2026-03-09 09:50:36 -07:00

flashmla.py

Reapply [Attention] Refactor check_and_update_config (#35122)

2026-03-09 07:17:14 -07:00

indexer.py

[DSV3.2][MTP] Optimize Indexer MTP handling (#36723)

2026-03-11 12:16:56 +08:00

rocm_aiter_mla_sparse.py

[ROCm][Perf] Enable sparse_mla's cudagraph on ROCm platform (#35719)

2026-03-10 09:14:35 -07:00

rocm_aiter_mla.py

AITER MLA backend: Avoid CPU sync in _build_decode (#35765)

2026-03-11 07:25:00 +00:00

sparse_utils.py

[Attention] Add FlashInfer Sparse MLA backend (#33451)

2026-02-12 17:21:54 +00:00

triton_mla.py

[Kernel] Add FP8 KV cache support to Triton MLA decode attention (#34597)

2026-03-12 08:32:34 -07:00

xpu_mla_sparse.py

Add XPU MLA Sparse backend for DeepSeek v3.2 (#33230)

2026-03-11 19:19:15 +08:00