vllm-project
[Frontend] [Core] perf: Automatically detect vLLM-tensorized model, update `tensorizer` to version 2.9.0
Automatically detect vLLM-tensorized model, update tensorizer to version 2.9.0
This PR accomplishes several things:
- Updates docstrings to account for tensorizer refactor in #4097 in the
tensorize_vllm_examples.pyexample script, and slight corrections to the docstrings of the new, refactored functions. - Allows models to be automatically inferred as a vLLM-tensorized model. Accomplishes this by placing a meta-tensor "footprint" in the serialized model, and removing it at runtime.
vllm_tensorizedas an arg has been removed. - Updates
tensorizerto the full release of 2.9.0.
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,LLMclass, 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.shto 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-requiredlabel 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!
@Yard1 @ywang96
Some QoL improvements for tensorizer and some corrected docstrings (as per the great refactor from @Yard1), and an update for tensorizer as version 1.9.0 is officially released. No longer need to specify if a model is vLLM-tensorized beforehand, as I've implemented a way for this to be inferred implicitly by registering a meta tensor into the model during serialization with a vllm-tensorized-marker and removing it during deserialization.
Further made some improvements with documentation. Important fixes explaining how to use tensorizer with the refactored changes (as the example script predates the refactor) so hoping to get eyes on this! Cheers :D
@ywang96 @Yard1
Will take a look once I have some bandwidth - thanks for the continuous contribution to vLLM!
