static_scaled_fp8_quant should not run when scale.numel is not 1

[eldarkurtic]

static_scaled_fp8_quant should not run when scale.numel() > 1. Right now, when scale is an array of values, static_scaled_fp8_quant will just use the first scale and ignore the rest of the array. This shouldn't happen silently, and probably best to fail and inform the user that scale must be of size 1.

[gemini-code-assist]

Summary of Changes

Hello @eldarkurtic, 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 submitted a change to improve the robustness of the FP8 quantization logic. This ensures that the static_scaled_fp8_quant function operates correctly by validating its input scale parameter, preventing silent misbehavior when an array of scales is inadvertently provided where a single scale is expected.

Highlights

• Input Validation for Static Quantization: I've updated the scaled_fp8_quant function in vllm/_custom_ops.py to enforce a stricter assertion for the scale tensor. Specifically, when the static quantization path is taken, the scale tensor must now explicitly have a numel() of 1, in addition to num_token_padding being None. This prevents static_scaled_fp8_quant from silently using only the first element of a multi-element scale tensor when a single scale is expected.

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 is currently in preview and 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 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

1. 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. ↩

[gemini-code-assist]

Code Review

The pull request modifies the condition for static scaled FP8 quantization to ensure that it only runs when the scale tensor has a single element. This change prevents the function from silently using only the first element of the scale tensor when it contains multiple values, and instead raises an error to inform the user that the scale must be of size 1.

[github-actions]

👋 Hi! Thank you for contributing to the vLLM project.

💬 Join our developer Slack at https://slack.vllm.ai to discuss your PR in #pr-reviews, coordinate on features in #feat- channels, or join special interest groups in #sig- channels.

Just a reminder: PRs would not trigger full CI run by default. Instead, it would only run fastcheck CI which starts running only a small and essential subset of CI tests to quickly catch errors. You can run other CI tests on top of those by going to your fastcheck build on Buildkite UI (linked in the PR checks section) and unblock them. If you do not have permission to unblock, ping simon-mo or khluu to add you in our Buildkite org.

Once the PR is approved and ready to go, your PR reviewer(s) can run CI to test the changes comprehensively before merging.

To run CI, PR reviewers can either: Add ready label to the PR or enable auto-merge.

🚀

[mgoin]

Thanks for finding this!