ZCG12345 45c3c279e2 moe_gating_top_k (#5271) ...

1. What this PR does / why we need it?
This PR supports the moe_gating_top_k operator, which enables
post-positioned renormalization (renorm) on the basis of softmax.
2. Does this PR introduce any user-facing change?
No user-facing changes are required.
3. How was this patch tested?
This patch was tested with the test_npu_moe_gating_top_k test case.
vLLM version: release/v0.13.0
vLLM main:
ad32e3e19c

---------

Signed-off-by: ZCG12345 <2097562023@qq.com>
Signed-off-by: zzzzwwjj <34335947+zzzzwwjj@users.noreply.github.com>
Co-authored-by: zzzzwwjj <34335947+zzzzwwjj@users.noreply.github.com>

2025-12-30 09:28:01 +08:00

..

310p

Drop torchair (#4814)

2025-12-10 09:20:40 +08:00

doctests

[Doc] Recover installation doc to use pip install (#4109)

2025-11-11 09:25:44 +08:00

models

[test]Corrected the Qwen3-Omni-30B-A3B-Instruct accuracy test configuration in nightly tests. (#5195)

2025-12-23 14:17:27 +08:00

multicard

update vllm pin to 12.27 (#5412)

2025-12-28 00:19:36 +08:00

nightly

moe_gating_top_k (#5271)

2025-12-30 09:28:01 +08:00

prompts

[CI/UT] Add test for chunk prefill and prefix cache on v1/AscendScheduler (#1505)

2025-07-02 16:57:03 +08:00

singlecard

[refactor] refactor model runner capture model (#5230)

2025-12-30 08:32:14 +08:00

vllm_interface

[E2E] Optimize the E2E test time. (#5294)

2025-12-26 14:17:50 +08:00

__init__.py

[Test] Clean up duplicate test for ascend scheduler (#1819)

2025-07-16 17:57:48 +08:00

common.sh

Increase doctest timeout to 300s and time print (#3041)

2025-09-19 20:26:00 +08:00

conftest.py

[Bugfix] Correctly handle the output shape in multimodal attention (#5443)

2025-12-27 18:42:46 +08:00

model_utils.py

[Misc] Clean up useless patch (#3320)

2025-10-09 14:07:26 +08:00

run_doctests.sh

Increase doctest timeout to 300s and time print (#3041)

2025-09-19 20:26:00 +08:00

utils.py

[Test] Remove VLLM_USE_V1 in example and tests (#1733)

2025-07-15 12:49:57 +08:00