modelscope / modelscope/ms-swift
请问vllm deploy的时候部署全量微调过的qwen3omni 会调用哪个forward呢
Open
Nobody has claimed this yet.
bug
stale
- Dominant language
- Python
- Stars
- 15.7k
- Forks
- 1.7k
- Avg merge
- 1d 16h
- Merged PRs (30d)
- 136
Description
Checklist / 检查清单
- I have searched existing issues, and this is a new bug report. / 我已经搜索过现有的 issues，确认这是一个新的 bug report。
Bug Description / Bug 描述
参考examples/deploy/agent/server.sh来部署推理微调后的qwen3omni，因为训练的时候改了forward，发现这样推理的时候forward走的不是原来的代码，请问这个时候forward应该修改哪里
How to Reproduce / 如何复现
最新版本swift vllm 0.13.0
Additional Information / 补充信息
No response
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start with examples/deploy/agent/server.sh and reproduce the deployment using the reported Swift and vLLM 0.13.0 versions. Trace the serving entry points to determine which forward implementation is invoked after full-parameter fine-tuning and where that behavior is selected. Done means documenting the call path and identifying the correct location to change or configure it.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Quiet
- Clarity
- Needs clarification
- Newbie friendliness
- 35/100