EngineX/xc-llm-ascend
3
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

moe_gating_top_k (#5271)

Browse Source 
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>
This commit is contained in:
ZCG12345
2025-12-30 09:28:01 +08:00
committed by GitHub
parent 15d73f248e
commit 45c3c279e2
34 changed files with 4791 additions and 22 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
tests/ut/worker/test_worker_v1.py
View File

@@ -670,7 +670,7 @@ class TestNPUWorker(TestBase):
(5000, 10000),
]
# 创建 worker mock
# Create worker mock
with patch.object(NPUWorker, "__init__", lambda x, **kwargs: None):
worker = NPUWorker()
worker.init_npu_memory = 8500