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

[Doc] Add Qwen3.5 fused MC2 known issue for 0.18.0 release (#8378)

Browse Source 
<!--  Thanks for sending a pull request!

BEFORE SUBMITTING, PLEASE READ
https://docs.vllm.ai/en/latest/contributing/overview.html

-->
### What this PR does / why we need it?
<!--
- Please clarify what changes you are proposing. The purpose of this
section is to outline the changes and how this PR fixes the issue.
If possible, please consider writing useful notes for better and faster
reviews in your PR.

- Please clarify why the changes are needed. For instance, the use case
and bug description.

- Fixes #
-->show known issues for Qwen3.5-397B

### Does this PR introduce _any_ user-facing change?
<!--
Note that it means *any* user-facing change including all aspects such
as API, interface or other behavior changes.
Documentation-only updates are not considered user-facing changes.
-->NO

### How was this patch tested?
<!--
CI passed with new added/existing test.
If it was tested in a way different from regular unit tests, please
clarify how you tested step by step, ideally copy and paste-able, so
that other reviewers can test and check, and descendants can verify in
the future.
If tests were not added, please describe why they were not added and/or
why it was difficult to add.
-->NA

---------

Signed-off-by: 李少鹏 <lishaopeng21@huawei.com>
This commit is contained in:
shaopeng-666
2026-04-17 22:54:21 +08:00
committed by GitHub
parent f2956ce944
commit f81f9a3c89
1 changed files with 5 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
docs/source/tutorials/models/Qwen3.5-397B-A17B.md
View File

@@ -599,3 +599,8 @@ vllm bench serve --model Eco-Tech/Qwen3.5-397B-A17B-w8a8-mtp --dataset-name rand
```
After about several minutes, you can get the performance evaluation result.
## Qwen3.5-397B-A17B Known issues
- Issue1: For single-node deployment scenario, when fused_mc2 is enabled, using multi-DP model deployment may cause garbled or empty outputs after the model triggers recomputation.When tuning performance by adjusting model parallelism, ensure that this fused operator is disabled when DP > 1. For PD deployment scenario，D nodes can avoid this problem by enabling the recompute scheduler.