update topk softmax #985
update topk softmax #985
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 @shihaobai, 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 refactors the fused_topk function by streamlining its internal operations. I've removed an unused placeholder variable and delegated the renormalize logic to the underlying sgl_ops.topk_softmax function, leading to cleaner and more focused code within fused_topk.
Highlights
- Code Simplification: I've removed the
token_expert_indiciestensor and its related operations from thefused_topkfunction. This tensor was previously declared and passed tosgl_ops.topk_softmaxbut was explicitly commented as 'Not used' and then deleted, indicating it was a placeholder or unnecessary for the current implementation. - Renormalization Delegation: The logic for renormalizing
topk_weights(lines 54-55 in the original code) has been removed fromfused_topk. Instead, therenormalizeboolean flag is now passed directly to thesgl_ops.topk_softmaxfunction, indicating that the renormalization responsibility has been moved into the underlyingtopk_softmaxoperation itself.
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
The fused_topk function was updated to use a newer version of the sgl_ops.topk_softmax kernel, which now handles re-normalization internally. The signature of sgl_ops.topk_softmax has changed, and the existing unit tests need to be updated to reflect this change.
| sgl_ops.topk_softmax( | ||
| topk_weights, | ||
| topk_ids, | ||
| token_expert_indicies, | ||
| gating_output.float(), # TODO(woosuk): Optimize this. | ||
| renormalize=renormalize, | ||
| ) |
There was a problem hiding this comment.
The sgl_ops.topk_softmax function signature has changed, now including renormalize as an argument. The test file unit_tests/common/fused_moe/test_softmax_topk.py needs to be updated to reflect this change, otherwise the tests will fail with a TypeError.
Please update the unit tests in unit_tests/common/fused_moe/test_softmax_topk.py to use the new API.
No description provided.