[Core] Adding Priority Scheduling

[apatke]

FILL IN THE PR DESCRIPTION HERE

There are three major changes implemented:


1. Addition of a new priority scheduling policy to the scheduler config. Also adds a user-defined priority variable to sequence.

2. All requests in the running queue and the waiting queue are sorted first based on this priority. If there is a tie, it falls back to the FCFS policy.

3. Force preemption of request from the running queue back into the waiting queue.
   If there are requests in the running queue whose priority is lower than the requests in the waiting queue, they are forcefully preempted out back into the waiting queue to allow immediate execution of the higher priority request.

@njhill @saurabhjha1 @youkaichao @simon-mo

FIX #6077 (link existing issues this PR will resolve)

BEFORE SUBMITTING, PLEASE READ THE CHECKLIST BELOW AND FILL IN THE DESCRIPTION ABOVE

---

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!

[njhill]

@apatke you need to run ./format.sh on the code to fix the linter errors.

[njhill]

Something we had been discussing is whether it would make sense for the API to take some kind of scheduing_params dataclass containing the priority, to allow for fields related to future scheduling policy additions without having to add them all as separate top-level parameters.

[apatke]

Performance slowdown from _schedule_priority_preemption is <4% with the priority policy for Llama 8B. No performance degradation when policy is not enabled.

priority: Throughput: 14.56 requests/s, 6052.59 tokens/s
fcfs: Throughput: 15.15 requests/s, 6299.22 tokens/s

[apatke]

@youkaichao Would you be able to take a look at the PR?

[njhill]

Thanks @apatke! I did a first pass.

As discussed, it's great that that this has no performance impact when the priority scheduling is disabled which is the most important thing.

Would be good to get @youkaichao's thoughts too.

[youkaichao]

will take a look when i have time :)

[njhill]

Thanks @apatke, could you resolve the new conflicts?

[youkaichao]

is this necessary to add in vllm's codebase? looks like the code duplication is large.

[njhill]

There is already a lot of duplication in our benchmarking and examples scripts ... could be a good separate task for someone to look at to streamline that. I will see if there's someone on my side who can look at it.

[youkaichao]

I give approval and hand it over to @njhill . I think it is fine since it does not affect default operation

[ZJUFangzh]

hi， why this priority scheduling not support AsyncLLMEngine？

[schoennenbeck]

@youkaichao @njhill Do you know if somebody is already working on supporting this in AsyncLLMEngine? If not I could go ahead open a PR.

[schoennenbeck]

Port can be found here: #8850