Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[misc] Allow partial prefix benchmarking & random input generation for prefix benchmarking #9929

Merged
merged 7 commits into from
Nov 18, 2024

Conversation

rickyyx
Copy link
Contributor

@rickyyx rickyyx commented Nov 1, 2024

This PR

  1. Allows a random generation for prompts when testing prefix caching
  2. Allows controlling exact ratio of prefix sharing among requests (rather than fully cached requests like before)

Copy link

github-actions bot commented Nov 1, 2024

👋 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 run fastcheck CI which starts running only a small and essential subset of CI tests to quickly catch errors. You can run other CI tests on top of those by going to your fastcheck build on Buildkite UI (linked in the PR checks section) and unblock them. If you do not have permission to unblock, ping simon-mo or khluu to add you in our Buildkite org.

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 do one of these:

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

🚀

@rickyyx
Copy link
Contributor Author

rickyyx commented Nov 1, 2024

Will run some more tests.

Copy link
Collaborator

@comaniac comaniac left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Otherwise LGTM

benchmarks/benchmark_prefix_caching.py Outdated Show resolved Hide resolved
Signed-off-by: rickyx <[email protected]>
Signed-off-by: rickyx <[email protected]>
Signed-off-by: rickyx <[email protected]>
Signed-off-by: rickyx <[email protected]>
Signed-off-by: rickyx <[email protected]>
Copy link

mergify bot commented Nov 8, 2024

This pull request has merge conflicts that must be resolved before it can be
merged. Please rebase the PR, @rickyyx.

https://docs.github.com/en/pull-requests/collaborating-with-pull-requests/working-with-forks/syncing-a-fork

@mergify mergify bot added the needs-rebase label Nov 8, 2024
Signed-off-by: rickyx <[email protected]>
@mergify mergify bot removed the needs-rebase label Nov 12, 2024
@comaniac comaniac added the ready ONLY add when PR is ready to merge/full CI is needed label Nov 12, 2024
@youkaichao youkaichao merged commit 90a6c75 into vllm-project:main Nov 18, 2024
36 of 42 checks passed
bigPYJ1151 pushed a commit to bigPYJ1151/vllm that referenced this pull request Nov 19, 2024
bigPYJ1151 pushed a commit to bigPYJ1151/vllm that referenced this pull request Nov 19, 2024
mikejuliet13 pushed a commit to mikejuliet13/vllm that referenced this pull request Nov 19, 2024
coolkp pushed a commit to coolkp/vllm that referenced this pull request Nov 20, 2024
KuntaiDu pushed a commit to KuntaiDu/vllm that referenced this pull request Nov 20, 2024
mfournioux pushed a commit to mfournioux/vllm that referenced this pull request Nov 20, 2024
rickyyx added a commit to rickyyx/vllm that referenced this pull request Nov 20, 2024
tlrmchlsmth pushed a commit to neuralmagic/vllm that referenced this pull request Nov 23, 2024
sleepwalker2017 pushed a commit to sleepwalker2017/vllm that referenced this pull request Dec 13, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
ready ONLY add when PR is ready to merge/full CI is needed
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants