Single sourced QuantizationSFLayout#1531
Conversation
There was a problem hiding this comment.
Summary of Changes
Hello @cyx-6, 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 aims to improve code maintainability and consistency by single-sourcing the QuantizationSFLayout enum. Previously, this enum was defined in multiple locations, leading to potential discrepancies and increased overhead for updates. By centralizing its definition into a new header file and updating all references, the change ensures a unified and consistent representation of quantization scale factor layouts across the codebase, simplifying future modifications and reducing the risk of errors.
Highlights
- Enum Centralization: The
QuantizationSFLayoutenum, previously duplicated across multiple C++ and Python files, has been centralized into a single C++ header file (include/flashinfer/fp4_layout.cuh). - Code Refactoring: Existing C++ files now reference the single-sourced
QuantizationSFLayoutusingusingdeclarations, removing redundant local definitions. - Cross-Language Alignment: The Python definition of
QuantizationSFLayouthas been updated to align with the new C++ enum, including new members likeSWIZZLED_8x4and adjusted integer values. - Configuration Updates: Default values for
QuantizationSFLayoutin relevant structs and test cases have been updated to reflect the new, more specific enum members (e.g.,SWIZZLED_128x4).
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 does a great job of single-sourcing the QuantizationSFLayout enum, which significantly improves code maintainability by removing duplication. The changes are applied consistently across both C++ and Python code.
I have a couple of minor suggestions for code improvement. Additionally, I've noticed a potential issue in the test files (tests/test_trtllm_allreduce_fusion.py and tests/test_trtllm_moe_allreduce_fusion.py). It appears they still reference the old comm.QuantizationSFLayout.SWIZZLED member, which has been removed in this PR. This will likely cause the tests to fail and should be corrected to use the new enum members.
| SWIZZLED_128x4 = 0 | ||
| SWIZZLED_8x4 = 1 | ||
| # Block scale factors are stored in linear layout (row-major). This is used in some trtllm-gen | ||
| # kernels standard. | ||
| LINEAR = 1 | ||
| LINEAR = 2 |
There was a problem hiding this comment.
For better type safety and to follow modern Python practices, consider changing this class to an enum.IntEnum. This would make the code more robust and expressive. You would need to add from enum import IntEnum at the top of the file and change the class definition to class QuantizationSFLayout(IntEnum):.
| // kernels standard. | ||
| LINEAR | ||
| }; | ||
| }; No newline at end of file |
There was a problem hiding this comment.
It's a common convention and good practice to end files with a newline character. This can prevent issues with some tools and compilers. Please add a newline at the end of the file.
<!-- .github/pull_request_template.md --> ## 📌 Description Currently comm modules and moe modules are not compiled in aot unittests, which results in lots of issues such as #1371 #1410, and #1530. This PR adds these modules to aot UT to make sure we capture the potential compilation error of these modules. #1531 (a bugfix) changes were ported into this PR to test together. ## 🔍 Related Issues #1371, #1410, #1530, #1531 ## 🚀 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 - [x] I have installed `pre-commit` by running `pip install pre-commit` (or used your preferred method). - [x] I have installed the hooks with `pre-commit install`. - [x] I have run the hooks manually with `pre-commit run --all-files` and fixed any reported issues. > If you are unsure about how to set up `pre-commit`, see [the pre-commit documentation](https://pre-commit.com/). ## 🧪 Tests - [x] Tests have been added or updated as needed. - [ ] All tests are passing (`unittest`, etc.). ## Reviewer Notes cc @nvpohanh @weireweire --------- Co-authored-by: Yaxing Cai <yaxingc@nvidia.com> Co-authored-by: Zihao <zihaoy@nvidia.com> Co-authored-by: Zihao Ye <expye@outlook.com>
|
Merged into #1528 |
📌 Description
Unified the
QuantizationSFLayoutto single sourced enum class.🔍 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