[4/n]decouple quantization implementation from vLLM dependency#9191
[4/n]decouple quantization implementation from vLLM dependency#9191zhyncs merged 7 commits intosgl-project:mainfrom
Conversation
Co-authored-by: AniZpZ <aniz1905@gmail.com>
Hongbosherlock
requested review from
BBuf,
Edwardf0t1,
HaiShaw,
Ying1123,
ch-wan,
ispobock,
kushanam,
merrymercy and
zhyncs
as code owners
![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 @Hongbosherlock, 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, part of a series, aims to decouple the AWQ and GPTQ quantization implementations from a direct dependency on vLLM. By refactoring the import paths for specific quantization kernels, it allows SGLang to manage these quantization methods independently, improving modularity and reducing external dependencies.
Highlights
- Decoupled Quantization Methods: Removed AWQ and GPTQ related configurations from the VLLM_QUANTIZATION_METHODS list, signifying their independence from vLLM.
- Direct Kernel Imports: Replaced imports of quantization operations from vllm._custom_ops with direct imports of corresponding kernels (e.g., awq_marlin_repack, gptq_gemm) from sgl_kernel.
- Streamlined GPTQ Method Handling: Eliminated the gptq_get_quant_method function and associated monkey patching, simplifying how GPTQ quantization methods are applied.
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. ↩
|
Warning Gemini encountered an error creating the review. You can try again by commenting |
|
The CI seems to still be using |
…roject#9191) Co-authored-by: AniZpZ <aniz1905@gmail.com> Co-authored-by: Yineng Zhang <me@zhyncs.com>
…roject#9191) Co-authored-by: AniZpZ <aniz1905@gmail.com> Co-authored-by: Yineng Zhang <me@zhyncs.com>
| TestFile("test_gguf.py", 96), | ||
| TestFile("test_gptqmodel_dynamic.py", 102), | ||
| TestFile("test_vllm_dependency.py", 185), | ||
| # TestFile("test_gguf.py", 96), |
There was a problem hiding this comment.
Can we add gguf support back?
cc @AniZpZ @Hongbosherlock ?
There was a problem hiding this comment.
we'll work on it
3 participants
Motivation
follow #8112
remove vllm dependency for AWQ and GPTQ quantization.
co-author:@AniZpZ
Modifications
Accuracy Tests
Benchmarking and Profiling
Checklist