Conversation
Summary of ChangesHello @yizhang2077, 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 addresses a potential Out-Of-Memory (OOM) issue within the radix tree cache by modifying how values are assigned to tree nodes. The core change involves introducing explicit cloning for Highlights
🧠 New Feature in Public Preview: You can now enable Memory to help Gemini Code Assist learn from your team's feedback. This makes future code reviews more consistent and personalized to your project's style. Click here to enable Memory in your admin console. 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
|
There was a problem hiding this comment.
Code Review
The pull request introduces .clone() calls when assigning value and host_value to TreeNode properties. This is a crucial change that addresses potential data corruption and out-of-memory (OOM) issues by ensuring that new nodes receive independent copies of tensor data rather than shared references. This prevents unintended modifications to node data when the original tensors or their slices are altered elsewhere in the program. The consistent application of .clone() across different insertion points in both hiradix_cache.py and mamba_radix_cache.py indicates a thorough fix for aliasing problems with mutable tensor values.
|
/tag-and-rerun-ci |
Motivation
fix missing part in #17191
Modifications
Accuracy Tests
Benchmarking and Profiling
Checklist
Review Process
/tag-run-ci-label,/rerun-failed-ci,/tag-and-rerun-ci