Fix modelopt FP8 create weights

[danielafrimi]

ModelOptFp8LinearMethod.create_weights() was missing input_size and output_size parameters, causing type error

in commit 80b2b3207, LinearMethodBase.create_weights() was updated to include input_size and output_size parameters. ModelOptFp8LinearMethod was never updated to match.

Fix 2: NemotronH is missing self.quant_config attribute
KV cache defaulted to bfloat16 instead of FP8, even when hf_quant_config.json specified kv_cache_quant_algo: "FP8". NemotronHForCausalLM didn't store self.quant_config = quant_config, so model_runner.py couldn't read kv_cache_quant_algo from the model.

[gemini-code-assist]

Summary of Changes

Hello @danielafrimi, 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 resolves a type error by updating the create_weights method signature in ModelOptFp8LinearMethod to match its base class. This ensures that the necessary input_size and output_size parameters are correctly handled, maintaining consistency and preventing runtime issues in the FP8 quantization process.

Highlights

• Method Signature Update: The create_weights method within ModelOptFp8LinearMethod has been updated to include input_size and output_size parameters. This change aligns its signature with the LinearMethodBase.create_weights() method, which was previously updated in commit 80b2b3202.
• Type Error Resolution: This synchronization of method signatures resolves a type error that occurred due to the missing parameters, ensuring correct parameter passing during the creation of FP8 quantized weights.

🧠 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.

Changelog

• python/sglang/srt/layers/quantization/modelopt_quant.py
  • Added input_size: int and output_size: int to the parameters of the create_weights function in ModelOptFp8LinearMethod.

Activity

• No human activity (comments, reviews, etc.) has been recorded for this pull request yet.

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 by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

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 pull request 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

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

This pull request correctly fixes a TypeError in ModelOptFp8LinearMethod.create_weights by adding the missing input_size and output_size parameters to match the base class signature. My feedback includes a minor suggestion to improve code clarity by marking these new, unused parameters as such, following common Python conventions.

[b8zhong]

/tag-and-rerun-ci