modelscope / modelscope/ms-swift
qwen3-vl-8b部署后使用--infer_backend vllm加速推理后内存消耗增加很多
Open
Nobody has claimed this yet.
question
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 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
使用--infer_backend vllm加速推理后，在推理时内存迅速增长，请求并发度8时vllm消耗的内存达到了60-70GB，请问这符合预期么？
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 by reproducing the qwen3-vl-8b deployment with --infer_backend vllm at concurrency 8, while measuring memory growth during inference. Determine whether the reported 60–70 GB usage is expected, then document the finding or identify the relevant cause and resolution.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning, performance
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Quiet
- Clarity
- Needs clarification
- Newbie friendliness
- 35/100