Remove assertions about per group quant fp8 #8717
Conversation
There was a problem hiding this comment.
Summary of Changes
Hello @fzyzcjy, 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!
I've made a targeted change to the FP8 quantization kernel by removing an assertion that was causing issues or was no longer necessary. This change specifically addresses a constraint on the input tensor's shape during per-group quantization, which should improve the flexibility and robustness of the quantization process, particularly for certain edge cases or configurations.
Highlights
- Assertion Removal in FP8 Quantization Kernel: I have removed a specific assertion
assert x.shape[-1] % (group_size * 4) == 0from thesglang_per_token_group_quant_fp8function. This assertion was previously conditional onscale_ue8m0and had aTODOcomment associated with it, indicating it needed to be addressed for a specific unit test case.
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 or fill out our survey to provide feedback.
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.
Code Review
This pull request removes an assertion from sglang_per_token_group_quant_fp8 related to scale_ue8m0. While this might be a cleanup of an obsolete check, the associated TODO comment and lack of explanation in the PR description raise concerns about potential silent failures in the underlying CUDA kernel. I've added a comment requesting clarification on why this assertion is no longer needed.
Motivation
Modifications
Accuracy Test
Benchmark & Profiling
Checklist