verl-project/verl

希望可以增加单独检查权重转换逻辑

Open

#6,414 opened on May 20, 2026

View on GitHub
 (1 comment) (0 reactions) (0 assignees)Python (3,940 forks)auto 404
help wanted

Repository metrics

Stars
 (21,533 stars)
PR merge metrics
 (Avg merge 5d) (146 merged PRs in 30d)

Description

我在尝试把slime的训练任务迁移到verl，但是发现权重转换有点问题，我想对这个进行调试，但是仍然需要足够规模的时间和显存来保证训练和推理的正常进行。请问有什么手段可以单独检查权重转换逻辑嘛？

slime里有--check-weight-update-equal配置来验证权重同步后的值是否正确。https://github.com/THUDM/slime/blob/main/docs/zh/developer_guide/debug.md

Contributor guide

Research direction
Study the weight conversion code in verl, investigate how slime's check weight update equal flag works, and propose a similar debugging mechanism to validate weight conversion logic.
Tech stack
python
Domain
backend
Issue type
Feature
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
2
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
1-2 days
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
Fresh
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
Clear
Prerequisites
Python
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
60