5 people f1899b2ffd [Bugfix][ROCm] AITER MLA: size MTP verification decode metadata for real qlen/dtype (#45227) ...

Signed-off-by: Edwin Lim <edwin.lim@mangoboost.io>
Signed-off-by: Chaemin Lim <chaemin.lim@mangoboost.io>
Signed-off-by: QinPR <1905873179@qq.com>
Co-authored-by: Edwin Lim <edwin.lim@mangoboost.io>
Co-authored-by: limeward <32970461+edwinlim0919@users.noreply.github.com>
Co-authored-by: QinPR <1905873179@qq.com>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

2026-07-30 20:50:34 -05:00

..

mla

[Bugfix][ROCm] AITER MLA: size MTP verification decode metadata for real qlen/dtype (#45227)

2026-07-30 20:50:34 -05:00

__init__.py

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

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

cpu_attn.py

[CPU] Fix FP8 attention scratchpad sizing (#50194)

2026-07-29 15:34:37 +08:00

fa_utils.py

Enable gfx1250 ROCm architecture (#46516)

2026-07-31 01:41:12 +00:00

flash_attn_diffkv.py

[2/N][KV-Cache Layout Refactor] Pack K/V into the content dim across attention backends (#44455)

2026-07-11 11:11:16 -04:00

flash_attn.py

[Attention] Integrate FlashAttention 4 SM100 headdim 256 support (#42669)

2026-07-27 18:25:50 +00:00

flashinfer.py

[Bugfix][Attention] Preserve post-load tensors across weight reloads (#48251)

2026-07-17 14:15:26 +08:00

flex_attention.py

[FlexAttention] Avoid encoder block-mask compile explosion (#50339)

2026-07-30 11:24:13 -04:00

gdn_attn.py

[Refactor] Move fla to third party (#48500)

2026-07-16 19:22:36 +01:00

hpc_attn.py

[Attention Backend] HPC_ATTN backend support mtp and dynamic scheduled attention (#47433)

2026-07-05 18:18:25 -07:00

linear_attn.py

[Feature] Support MTP speculative decoding for Bailing hybrid models (#44880)

2026-07-06 10:38:50 +08:00

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

[Core] Ensure memory is pinned prior to async h2d copy (#45424)

2026-06-20 20:02:24 -07:00

mamba_attn.py

[Kernel] ReplaySSM: cache SSM inputs for faster Mamba2 standard decode (#48018)

2026-07-24 09:39:49 -07:00

registry.py

[Attention Backend] add HPC-Ops Attention backend (#46020)

2026-06-30 18:17:43 +08:00

rocm_aiter_fa.py

Enable gfx1250 ROCm architecture (#46516)

2026-07-31 01:41:12 +00:00

rocm_aiter_unified_attn.py

[Model][Hardware][AMD]: Part 1/2 -> Enable e2e QK Norm + RoPE + KV Cache runtime fusion for Qwen3-30B-A3B on ROCM_AITER_FA, and ROCM_AITER_UNIFIED_ATTN (#42749)

2026-07-16 17:39:04 -05:00

rocm_attn.py

[Attention] Make sliding-window support an explicit backend capability (#48011)

2026-07-13 01:07:56 -07:00

short_conv_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

triton_attn_diffkv.py

[2/N][KV-Cache Layout Refactor] Pack K/V into the content dim across attention backends (#44455)

2026-07-11 11:11:16 -04:00

triton_attn.py

[Misc] Rename VLLM_TRITON_ATTN_USE_TD to VLLM_TRITON_USE_TD (#45781)

2026-07-14 10:32:57 +00:00

turboquant_attn.py

[2/N][KV-Cache Layout Refactor] Pack K/V into the content dim across attention backends (#44455)

2026-07-11 11:11:16 -04:00

utils.py

[Core] Add MRV2 virtual-batch PCP for MLA (#46570)

2026-07-19 02:53:15 +00:00