modelscope / modelscope/ms-swift
on policy训练异步rollout
Open
Nobody has claimed this yet.
stale
- Dominant language
- Python
- Stars
- 15.7k
- Forks
- 1.7k
- Avg merge
- 1d 16h
- Merged PRs (30d)
- 136
Description
目前看on policy异步仅支持vllm框架，像其他比如lmdeploy能否也支持呢？感觉vllm对torch环境太敏感了，不太好用。比如on policy distillation中只有打开vllm的开关，能否加入lmdeploy实现异步rollout呢？
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 locating the on-policy asynchronous rollout entry point and the on-policy distillation option that currently enables vLLM. Compare how rollout backends are integrated and determine the required lmdeploy path; done means asynchronous rollout can use lmdeploy for the described on-policy distillation scenario.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 35/100