fix missing enable_pdl argument in trtllm-gen fp4 moe #1480
Conversation
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
There was a problem hiding this comment.
Summary of Changes
Hello @IwakuraRein, 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 regression introduced in a previous change by adding the enable_pdl argument to several Mixture-of-Experts (MoE) related function signatures within flashinfer/fused_moe/core.py. This ensures that the enable_pdl argument is properly propagated and utilized for trtllm-gen fp4 moe operations, resolving a missing argument issue.
Highlights
- Function Signature Update: The
enable_pdl: Optional[bool] = Noneargument was added to the signature of the_fake_cutlass_fused_moe_sm100function. - Function Signature Update: The
enable_pdl: Optional[bool] = Noneargument was added to the signature of the_fake_trtllm_fp8_per_tensor_scale_moefunction. - Function Signature Update: The
enable_pdl: Optional[bool] = Noneargument was added to the signature of the_fake_trtllm_fp8_block_scale_moefunction. - Function Signature Update: The
enable_pdl: Optional[bool]andoutput: Optional[torch.Tensor]arguments were added to the signature of the_fake_trtllm_fp4_block_scale_moefunction. - Function Signature Update: The
enable_pdl: Optional[bool] = Noneandoutput: Optional[torch.Tensor] = Nonearguments were added to the signature of thetrtllm_fp4_block_scale_moefunction. - Argument Propagation Fix: The
enable_pdlargument is now correctly passed fromtrtllm_fp4_block_scale_moeto its internal call to_fake_trtllm_fp4_block_scale_moe.
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.
Code Review
This pull request correctly adds the missing enable_pdl argument to several fused MoE functions, ensuring it's propagated as intended. The changes are straightforward and address the issue described. I've pointed out one minor issue in a fake operator's signature where default values for new arguments are missing, which could cause issues with torch.compile.
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
📌 Description
Fix the missing
enable_pdlargument introduced in #1446 .🔍 Related Issues
🚀 Pull Request Checklist
Thank you for contributing to FlashInfer! Before we review your pull request, please make sure the following items are complete.
✅ Pre-commit Checks
pre-commitby runningpip install pre-commit(or used your preferred method).pre-commit install.pre-commit run --all-filesand fixed any reported issues.🧪 Tests
unittest, etc.).Reviewer Notes