-
Notifications
You must be signed in to change notification settings - Fork 501
[Bug] KVCache: fix metrics #1450
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
[Bug] KVCache: fix metrics #1450
Conversation
Signed-off-by: Haiyang Shi <[email protected]>
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Summary of Changes
Hello @DwyaneShi, 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 bug in the KVCache metrics system by refactoring how metric attributes are initialized. Previously, some metric counters and lists were initialized as class-level defaults, which could lead to incorrect state management. The changes move these initializations into the respective class constructors, ensuring that each instance of OpMetrics, UsageMetrics, and BaseCacheMetrics starts with a clean and correct state for its metrics, thereby improving the accuracy of metric collection.
Highlights
- Metric Initialization Refactor: Moved the initialization of various metric counters and lists (e.g.,
num_ops,num_errors,num_prefixes,num_tokens,num_fetched_tokens,capacity_nbytes,used_nbytes,num_tokens_hit,num_tokens_miss) from class-level default assignments to instance-level initialization within the__init__methods ofOpMetrics,UsageMetrics, andBaseCacheMetrics. - Bug Fix: This change specifically fixes a bug where metric values might not have been correctly reset or managed across different instances or uses, ensuring accurate metric collection for KVCache operations.
Using Gemini Code Assist
The 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 in your pull request via creating an issue comment (i.e. comment on the pull request page) using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands.
| Feature | Command | Description |
|---|---|---|
| Code Review | /gemini review |
Performs a code review for the current pull request in its current state. |
| Pull Request Summary | /gemini summary |
Provides a summary of the current pull request in its current state. |
| Comment | @gemini-code-assist | Responds in comments when explicitly tagged, both in issue comments and review comments. |
| Help | /gemini help |
Displays a list of available commands. |
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 .gemini/ folder in the base of the repository. Detailed instructions can be found here.
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
-
Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Code Review
This pull request correctly addresses a critical issue with metric tracking by moving the initialization of metric attributes from class-level to instance-level within the __init__ methods. This prevents state from being shared across different metric instances, ensuring accurate and independent metric collection for operations like 'put', 'get', and 'exists'. The changes are applied consistently across OpMetrics, UsageMetrics, and BaseCacheMetrics.
I've identified a couple of related inconsistencies in the reset() logic for metrics which I've detailed in my comments. Addressing these would further improve the correctness and consistency of the metrics system.
Signed-off-by: Haiyang Shi <[email protected]> Co-authored-by: Haiyang Shi <[email protected]>
* [Chore] KVCache: downgrade to cuda 12.1 (#1444) Signed-off-by: Haiyang Shi <[email protected]> Co-authored-by: Haiyang Shi <[email protected]> * [Bug] KVCache: fix metrics (#1450) Signed-off-by: Haiyang Shi <[email protected]> Co-authored-by: Haiyang Shi <[email protected]> --------- Signed-off-by: Haiyang Shi <[email protected]> Co-authored-by: Haiyang Shi <[email protected]>
Pull Request Description
[Please provide a clear and concise description of your changes here]
Related Issues
Resolves: #[Insert issue number(s)]
Important: Before submitting, please complete the description above and review the checklist below.
Contribution Guidelines (Expand for Details)
We appreciate your contribution to aibrix! To ensure a smooth review process and maintain high code quality, please adhere to the following guidelines:
Pull Request Title Format
Your PR title should start with one of these prefixes to indicate the nature of the change:
[Bug]: Corrections to existing functionality[CI]: Changes to build process or CI pipeline[Docs]: Updates or additions to documentation[API]: Modifications to aibrix's API or interface[CLI]: Changes or additions to the Command Line Interface[Misc]: For changes not covered above (use sparingly)Note: For changes spanning multiple categories, use multiple prefixes in order of importance.
Submission Checklist
By submitting this PR, you confirm that you've read these guidelines and your changes align with the project's contribution standards.