Conversation
Contributor
Summary of ChangesHello @hiyuchang, I'm Gemini Code Assist1! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed! This pull request lays the groundwork for integrating LoRA (Low-Rank Adaptation) functionality, particularly for vLLM-based models, to facilitate more efficient and flexible large language model operations. It extends the system's configuration capabilities to define LoRA settings, modifies core model interaction logic to apply LoRA adapters during inference, and introduces helper utilities for LoRA management. The current state is a Work In Progress, with further development planned for evaluation and alternative synchronization methods. Highlights
Using Gemini Code AssistThe full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips. Invoking Gemini You can request assistance from Gemini at any point by creating a comment using either
Customization To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a Limitations & Feedback Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here. You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension. Footnotes
|
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
Contributor
There was a problem hiding this comment.
Code Review
This pull request introduces LoRA (Low-Rank Adaptation) support, which is a significant feature addition. The changes span across configuration, model wrappers, and the training pipeline to accommodate LoRA models. Overall, the implementation looks promising, but there are several critical issues and areas for improvement regarding correctness, robustness, and code quality that need to be addressed. I've identified a critical bug in the generate methods that would cause a runtime error, as well as potential issues with configuration logic and code maintainability. Please see the detailed comments for specific feedback and suggestions.
Collaborator
Author
|
/unittest-all |
Collaborator
Author
|
/unittest-all |
hiyuchang
commented
Sep 22, 2025
Summary
Failed Tests
Skipped
Tests
Github Test Reporter by CTRF 💚 |
Collaborator
Author
|
/unittest-module-common |
Summary
Tests
Github Test Reporter by CTRF 💚 |
pan-x-c
reviewed
Sep 22, 2025
pan-x-c
reviewed
Sep 22, 2025
Collaborator
Author
|
/unittest-all |
Summary
Failed Tests
Skipped
Tests
Github Test Reporter by CTRF 💚 |
Collaborator
Author
|
/unittest-module-common |
Collaborator
Author
|
/unittest-module-trainer |
Summary
Tests
Github Test Reporter by CTRF 💚 |
Collaborator
Author
|
/unittest-module-trainer |
Summary
Skipped
Tests
Github Test Reporter by CTRF 💚 |
pan-x-c
reviewed
Sep 24, 2025
pan-x-c
reviewed
Sep 24, 2025
There was a problem hiding this comment.
Pull Request Overview
This PR adds LoRA (Low-Rank Adaptation) mode support to Trinity, enabling parameter-efficient fine-tuning for training and evaluation. The implementation supports checkpoint synchronization and provides examples with recommended YAML configurations.
Key Changes:
- Added LoRA configuration support through
lora_configsin model configuration - Implemented LoRA request handling in vLLM model wrapper with dynamic LoRA path management
- Added utility functions for creating dummy LoRA adapters when no path is provided
Reviewed Changes
Copilot reviewed 13 out of 13 changed files in this pull request and generated 2 comments.
Show a summary per file
| File | Description |
|---|---|
trinity/utils/lora_utils.py |
New utility for creating dummy LoRA adapters |
trinity/common/config.py |
Added LoRA configuration classes and automatic setup logic |
trinity/common/verl_config.py |
Enhanced configuration synchronization for LoRA support |
trinity/common/models/vllm_model.py |
Added LoRA request handling and model synchronization |
trinity/common/models/model.py |
Updated ModelWrapper to support LoRA requests |
trinity/trainer/verl_trainer.py |
Added conditional reference policy computation logic |
trinity/manager/synchronizer.py |
Added LoRA enable flag |
trinity/explorer/explorer.py |
Added LoRA enable flag |
trinity/explorer/workflow_runner.py |
Pass LoRA enable flag to ModelWrapper |
tests/trainer/trainer_test.py |
Added comprehensive LoRA training and benchmarking tests |
tests/tools.py |
Added LoRA configuration helper and improved dataset comments |
examples/grpo_lora_gsm8k/ |
New example with YAML configuration and documentation |
Tip: Customize your code reviews with copilot-instructions.md. Create the file or learn how to get started.
Collaborator
|
/unittest-module-trainer |
Summary
Failed Tests
Skipped
Tests
Github Test Reporter by CTRF 💚 |
Collaborator
Author
|
/unittest-module-trainer |
Summary
Skipped
Tests
Github Test Reporter by CTRF 💚 |
Collaborator
|
/unittest-module-common |
Summary
Tests
Github Test Reporter by CTRF 💚 |
pan-x-c
approved these changes
Sep 24, 2025
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Description
As the title says.
sync_method=Checkpointsync_method=NCCLChecklist
Please check the following items before code is ready to be reviewed.