modelscope / modelscope/ms-swift
基于4.0版本微调qwen3.5-4b模型LoRA，merge之后使用主分支的vllm启动出错
Open
Nobody has claimed this yet.
question
- 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 question or discussion topic. / 我已经搜索过现有的 issues，确认这是一个新的问题与讨论。
Question Description / 问题描述
merge代码如下：swift export
--adapters ./output/v3-20260305-150143/checkpoint-964
--merge_lora true
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
The issue provides only the swift export --adapters ./output/v3-20260305-150143/checkpoint-964 --merge_lora true command and says that main-branch vLLM startup fails afterward. Start by reproducing the export and startup flow, then collect the missing error details; done means the merged Qwen3.5-4B LoRA model starts successfully with the main branch.
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
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100