[Draft] proposal for ipex quant support

[jikunshang]

Intel® Extension for PyTorch extends PyTorch with up-to-date features optimizations for an extra performance boost on Intel hardware. it will also provide some quantization optimization in the near future and I want to proposal how to integrate this into vllm to benefit for both Intel cpu and gpu.

Here are the details:

1. ipex will provide a process_weights_after_loading interface to optimize weight's shape and/or layout(just like compressed tensor library done) which could perform best on Intel hardware. We will call this API once model get loaded in cpu_model_runner/xou_model_runner.
2. ipex will provide some quantizaion kernels like awq_gemm, gptq_gemm, and we will call these api in linear method classes(eg: awq.py AWQLinearMethod::apply())

---

PR Checklist (Click to Expand)

Thank you for your contribution to vLLM! Before submitting the pull request, please ensure the PR meets the following criteria. This helps vLLM maintain the code quality and improve the efficiency of the review process.

PR Title and Classification

Only specific types of PRs will be reviewed. The PR title is prefixed appropriately to indicate the type of change. Please use one of the following:

• [Bugfix] for bug fixes.
• [CI/Build] for build or continuous integration improvements.
• [Doc] for documentation fixes and improvements.
• [Model] for adding a new model or improving an existing model. Model name should appear in the title.
• [Frontend] For changes on the vLLM frontend (e.g., OpenAI API server, LLM class, etc.)
• [Kernel] for changes affecting CUDA kernels or other compute kernels.
• [Core] for changes in the core vLLM logic (e.g., LLMEngine, AsyncLLMEngine, Scheduler, etc.)
• [Hardware][Vendor] for hardware-specific changes. Vendor name should appear in the prefix (e.g., [Hardware][AMD]).
• [Misc] for PRs that do not fit the above categories. Please use this sparingly.

Note: If the PR spans more than one category, please include all relevant prefixes.

Code Quality

The PR need to meet the following code quality standards:

• We adhere to Google Python style guide and Google C++ style guide.
• Pass all linter checks. Please use format.sh to format your code.
• The code need to be well-documented to ensure future contributors can easily understand the code.
• Include sufficient tests to ensure the project to stay correct and robust. This includes both unit tests and integration tests.
• Please add documentation to docs/source/ if the PR modifies the user-facing behaviors of vLLM. It helps vLLM user understand and utilize the new features or changes.

Notes for Large Changes

Please keep the changes as concise as possible. For major architectural changes (>500 LOC excluding kernel/data/config/test), we would expect a GitHub issue (RFC) discussing the technical design and justification. Otherwise, we will tag it with rfc-required and might not go through the PR.

What to Expect for the Reviews

The goal of the vLLM team is to be a transparent reviewing machine. We would like to make the review process transparent and efficient and make sure no contributor feel confused or frustrated. However, the vLLM team is small, so we need to prioritize some PRs over others. Here is what you can expect from the review process:

• After the PR is submitted, the PR will be assigned to a reviewer. Every reviewer will pick up the PRs based on their expertise and availability.
• After the PR is assigned, the reviewer will provide status update every 2-3 days. If the PR is not reviewed within 7 days, please feel free to ping the reviewer or the vLLM team.
• After the review, the reviewer will put an action-required label on the PR if there are changes required. The contributor should address the comments and ping the reviewer to re-review the PR.
• Please respond to all comments within a reasonable time frame. If a comment isn't clear or you disagree with a suggestion, feel free to ask for clarification or discuss the suggestion.

Thank You

Finally, thank you for taking the time to read these guidelines and for your interest in contributing to vLLM. Your contributions make vLLM a great tool for everyone!

[github-actions]

👋 Hi! Thank you for contributing to the vLLM project.
Just a reminder: PRs would not trigger full CI run by default. Instead, it would only trigger fastcheck CI to run, which consists only a small and essential subset of tests to quickly catch errors with the flexibility to run extra individual tests on top (you can do this by unblocking test steps in the Buildkite run).

Full CI run is still required to merge this PR so once the PR is ready to go, please make sure to run it. If you need all test signals in between PR commits, you can trigger full CI as well.

To run full CI, you can do one of these:

• Comment /ready on the PR
• Add ready label to the PR
• Enable auto-merge.

🚀

[jgong5]

It sounds like a common mechanism, not specific to Intel devices and IPEX, to allow the model parameters to be preprocessed by the backend during model initialization? Would it be possible for vLLM to support this mechanism in a more general manner?

[jikunshang]

It sounds like a common mechanism, not specific to Intel devices and IPEX, to allow the model parameters to be preprocessed by the backend during model initialization? Would it be possible for vLLM to support this mechanism in a more general manner?

update a little bit. move post_process to cpu_model_runner/xpu_model_runner makes more sense. Please take a look again, thanks!
cc @ganyi1996ppo

[robertgshaw2-neuralmagic]

Hey! This is great

for fp16 compute, we use a CustomOp interface for the other backends. See for example #6289 from @WoosukKwon

I think it would be nice if we could leverage this framework for quantization as well?