Skip to content

P/D Stable Branch #85

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

Open
wants to merge 32 commits into
base: main
Choose a base branch
from
Open

P/D Stable Branch #85

wants to merge 32 commits into from

Conversation

robertgshaw2-redhat
Copy link
Collaborator

@robertgshaw2-redhat robertgshaw2-redhat commented May 14, 2025

SUMMARY:

  • ALL BUGFIXES SHOULD GO HERE

mgoin and others added 27 commits May 3, 2025 08:42
Signed-off-by: mgoin <mgoin64@gmail.com>
Signed-off-by: Nick Hill <nhill@redhat.com>
Signed-off-by: mgoin <mgoin64@gmail.com>
Signed-off-by: mgoin <mgoin64@gmail.com>
Signed-off-by: mgoin <mgoin64@gmail.com>
Signed-off-by: mgoin <mgoin64@gmail.com>
Signed-off-by: Nick Hill <nhill@redhat.com>
Signed-off-by: Nick Hill <nhill@redhat.com>
Signed-off-by: mgoin <mgoin64@gmail.com>
Signed-off-by: Nick Hill <nhill@redhat.com>
Signed-off-by: mgoin <mgoin64@gmail.com>
Signed-off-by: mgoin <mgoin64@gmail.com>
Signed-off-by: mgoin <mgoin64@gmail.com>
Signed-off-by: Nick Hill <nhill@redhat.com>
Signed-off-by: Nick Hill <nhill@redhat.com>
Signed-off-by: Nick Hill <nhill@redhat.com>
Signed-off-by: mgoin <mgoin64@gmail.com>
Signed-off-by: mgoin <mgoin64@gmail.com>
Signed-off-by: Nick Hill <nhill@redhat.com>
Signed-off-by: mgoin <mgoin64@gmail.com>
This was there originally but inadvertently dropped

Signed-off-by: Nick Hill <nhill@redhat.com>
…#79)

* Benchmark one concurrent req

Signed-off-by: Tyler Michael Smith <tyler@neuralmagic.com>

* Updates

Signed-off-by: Tyler Michael Smith <tyler@neuralmagic.com>

* restore

Signed-off-by: Tyler Michael Smith <tyler@neuralmagic.com>

* Improve random requests, switch up initial test

Signed-off-by: Tyler Michael Smith <tyler@neuralmagic.com>

---------

Signed-off-by: Tyler Michael Smith <tyler@neuralmagic.com>
Signed-off-by: Nick Hill <nhill@redhat.com>
Requires version of LMCache with the corresponding changes

Signed-off-by: Nick Hill <nhill@redhat.com>
Signed-off-by: Nick Hill <nhill@redhat.com>
Signed-off-by: Nick Hill <nhill@redhat.com>
Signed-off-by: rshaw@neuralmagic.com <robertgshaw2@gmail.com>
Copy link

👋 Hi! Thank you for contributing to the vLLM project.

💬 Join our developer Slack at https://slack.vllm.ai to discuss your PR in #pr-reviews, coordinate on features in #feat- channels, or join special interest groups in #sig- channels.

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 either: Add ready label to the PR or enable auto-merge.

🚀

Signed-off-by: Nick Hill <nhill@redhat.com>
njhill and others added 3 commits May 16, 2025 07:51
[BugFix] Fix ordering of KVConnector finished send/rcv sets
The MultiKVConnector impl keeps track of cases where multiple connectors are async saving the same request, but this state needs to be shared from the scheduler side to the worker side.

Signed-off-by: Nick Hill <nhill@redhat.com>
* [BugFix] Fix handling of num_computed_tokens with connector

vllm-project#18001 changed the behaviour subtly and broke some multi-connector cases.

This change ensures we don't call the connector get_num_new_matched_tokens method a second time for a given request after an async load has completed.

Signed-off-by: Nick Hill <nhill@redhat.com>

* fix linting

Signed-off-by: Nick Hill <nhill@redhat.com>

* handle full cache hit on P/D decode worker case

Signed-off-by: Nick Hill <nhill@redhat.com>

* fix comment wording

Co-authored-by: Nicolò Lucchesi <nicolo.lucchesi@gmail.com>

---------

Signed-off-by: Nick Hill <nhill@redhat.com>
Co-authored-by: Nicolò Lucchesi <nicolo.lucchesi@gmail.com>
* updated

Signed-off-by: rshaw@neuralmagic.com <robertgshaw2@gmail.com>

* cleanup issue

Signed-off-by: rshaw@neuralmagic.com <robertgshaw2@gmail.com>

---------

Signed-off-by: rshaw@neuralmagic.com <robertgshaw2@gmail.com>
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.

4 participants