agentscope-ai/Trinity-RFT

Reward function中的Reward Model应该在哪里初始化？

Open

#312 opened on Oct 10, 2025

View on GitHub
 (2 comments) (0 reactions) (0 assignees)Python (70 forks)github user discovery
good first issue

Repository metrics

Stars
 (648 stars)
PR merge metrics
 (PR metrics pending)

Description

Reward function中的Reward Model在哪里初始化是最好的呢；我目前是在workflow类下初始化的，但是它只能加载到cpu，然后推理打分时会非常非常慢，以至于超时报错

Contributor guide

Research direction
Investigate how to move the Reward Model initialization to GPU. Check the framework's model loading utilities and ensure the device is set to CUDA if available. Look for existing examples of GPU initialization in other parts of the codebase.
Tech stack
python
Domain
aimachine learning
Issue type
Performance
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.
1-3 hours
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
Active
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
Clear
Prerequisites
PythonPyTorch
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
70