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

speedup hash_of_block function #8935

Open
wants to merge 4 commits into
base: main
Choose a base branch
from

Conversation

flc666star
Copy link

The current time complexity of the hash_of_block function is O(n^2). This PR aimed to optimize it to O(n) by including the hash of the predecessor block in the calculation, in addition to the tokens of current block when calculating its hash.

Copy link

👋 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.

🚀

@DarkLight1337
Copy link
Member

Can you check whether this is still necessary with the introduction of block_manager_v2?

@comaniac
Copy link
Collaborator

Can you check whether this is still necessary with the introduction of block_manager_v2?

Echo on this. As we plan to deprecate block manager v1 in a few week, it would be better to focus on block manager v2. Also cc @sroy745 @rickyyx as you may be interested in this.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants