[Refactor] Create a function util and cache the results for has_deepgemm, has_deepep, has_pplx
#20187
Conversation
Signed-off-by: yewentao256 <zhyanwentao@126.com>
|
👋 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 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 🚀 |
There was a problem hiding this comment.
Summary of Changes
Hello @yewentao256, 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 way optional kernel availability is checked within the vLLM project. It introduces a cached utility function to avoid redundant calls to importlib.util.find_spec, improving performance and code readability. The changes affect multiple files related to fused MoE layers and quantization, ensuring consistent and efficient kernel detection.
Highlights
- Refactor: Created a utility function
_has_modulewith caching to check for the availability of optional kernel packages (pplx_kernels, deep_ep, deep_gemm). - Code Improvement: Replaced direct calls to
importlib.util.find_specwith the new cached utility functionhas_pplx,has_deepep, andhas_deep_gemmin multiple files. - Dependency Management: Removed unnecessary
importlib.utilimports from several files.
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
-
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 is a nice refactoring that centralizes and caches the checks for optional dependencies (deep_gemm, deepep, pplx_kernels), which should improve performance by avoiding repeated calls to importlib.util.find_spec.
However, the current implementation introduces a critical circular import dependency between vllm/model_executor/layers/fused_moe/utils.py and vllm/model_executor/layers/quantization/utils/fp8_utils.py. I've left a comment with details on how to resolve this by relocating the new utility functions to a lower-level module. Once that's addressed, this will be a solid improvement to the codebase.
Signed-off-by: yewentao256 <zhyanwentao@126.com>
vllm/utils.py
Outdated
| @cache | ||
| def _has_module(module_name: str) -> bool: | ||
| """Return True if *module_name* can be found in the current environment. | ||
|
|
||
| The result is cached so that subsequent queries for the same module incur | ||
| no additional overhead. | ||
| """ | ||
| return importlib.util.find_spec(module_name) is not None | ||
|
|
||
|
|
||
| def has_pplx() -> bool: | ||
| """Whether the optional `pplx_kernels` package is available.""" | ||
|
|
||
| return _has_module("pplx_kernels") | ||
|
|
||
|
|
||
| def has_deepep() -> bool: | ||
| """Whether the optional `deep_ep` package is available.""" | ||
|
|
||
| return _has_module("deep_ep") | ||
|
|
||
|
|
||
| def has_deep_gemm() -> bool: | ||
| """Whether the optional `deep_gemm` package is available.""" | ||
|
|
||
| return _has_module("deep_gemm") |
There was a problem hiding this comment.
Nit/future work: I think with these new import checks and the above torch version check, it would be nice to pull these into a separate import_utils.py file like Transformers to make it clear for new libraries to add there https://github.com/huggingface/transformers/blob/main/src/transformers/utils/import_utils.py#L386
There was a problem hiding this comment.
Sounds a great idea, we can move these import utils together, I can work on this later. Including is_in_ray_actor and all other util functions we have.
Signed-off-by: yewentao256 <zhyanwentao@126.com>
…gemm`, `has_deepep`, `has_pplx` (vllm-project#20187) Signed-off-by: yewentao256 <zhyanwentao@126.com>
…gemm`, `has_deepep`, `has_pplx` (vllm-project#20187) Signed-off-by: yewentao256 <zhyanwentao@126.com> Signed-off-by: avigny <47987522+avigny@users.noreply.github.com>
…gemm`, `has_deepep`, `has_pplx` (vllm-project#20187) Signed-off-by: yewentao256 <zhyanwentao@126.com>
Purpose
Fixes #20133