GuoRen868 4bd1030842 [Kernel] add custom op DispatchGmmCombineDecode (#4139) ...

#### What this PR does / why we need it?
add custom opapi DispatchGmmCombineDecode for A3, include kernel inpl,
python Api, pytest.

vLLM version: v0.11.0
vLLM main:
24d6314718


- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c

Signed-off-by: wangqiankun <wangqiankun13@huawei.com>
Co-authored-by: wangqiankun <wangqiankun13@huawei.com>
Co-authored-by: wangxiyuan <wangxiyuan1007@gmail.com>

2025-12-06 17:33:14 +08:00

..

_templates/sections

[Doc] add v0.9.1 release note (#2646)

2025-09-03 18:04:27 +08:00

assets

[docs] [P/D] add feature guide for disaggregated-prefill (#3950)

2025-11-10 09:31:30 +08:00

community

[Doc] Update vLLM version in doc (#4691)

2025-12-05 08:59:41 +08:00

developer_guide

add hyperlink (#4588)

2025-12-02 14:09:03 +08:00

locale/zh_CN/LC_MESSAGES

[feature] vllm-ascend support msprobe (eager mode dump) (#4241)

2025-11-24 21:58:31 +08:00

logos

[Doc] Add sphinx build for vllm-ascend (#55)

2025-02-13 18:44:17 +08:00

tutorials

【main】[Doc]add 2P1D instruction for single node (#4716)

2025-12-05 18:35:18 +08:00

user_guide

fix typo (#4657)

2025-12-03 11:56:47 +08:00

conf.py

upgrade vLLM to 0.12.0 tag (#4647)

2025-12-03 23:43:05 +08:00

faqs.md

[Doc] add release note for v0.11.0rc3 (#4646)

2025-12-03 11:49:44 +08:00

index.md

[feature] vllm-ascend support msprobe (eager mode dump) (#4241)

2025-11-24 21:58:31 +08:00

installation.md

[Kernel] add custom op DispatchGmmCombineDecode (#4139)

2025-12-06 17:33:14 +08:00

quick_start.md

[Doc] Refactor the DeepSeek-V3.2-Exp tutorial. (#3871)

2025-11-04 18:58:33 +08:00