Skip to content

Improve enable chunked_prefill & prefix_caching logic. #26623

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.

Sign up for GitHub

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

Jump to bottom
Merged
merged 72 commits into from
Nov 28, 2025
Merged

Improve enable chunked_prefill & prefix_caching logic. #26623

merged 72 commits into from
Nov 28, 2025

Conversation

@noooop
Copy link
Collaborator

@noooop noooop commented Oct 11, 2025 •
edited by github-actions bot
Loading

Purpose

Improve enable chunked_prefill & prefix_caching logic.

Test Plan

pytest -s -vvv tests/test_config.py::test_is_chunked_prefill_supported
pytest -s -vvv tests/test_config.py::test_is_prefix_caching_supported
pytest -s -vvv tests/models/language/pooling/test_auto_prefix_cache_support.py

Test Result

pass

Essential Elements of an Effective PR Description Checklist
  • The purpose of the PR, such as "Fix some issue (link existing issues this PR will resolve)".
  • The test plan, such as providing test command.
  • The test results, such as pasting the results comparison before and after, or e2e results
  • (Optional) The necessary documentation update, such as updating supported_models.md and examples for a new model.
  • (Optional) Release notes update. If your change is user facing, please update the release notes draft in the Google Doc.

@noooop noooop changed the title [Model][0/N] Improve all pooling task | Improve enable chunked_prefill & prefix_caching logic. [Model][4/N] Improve all pooling task | Improve enable chunked_prefill & prefix_caching logic. Oct 11, 2025
This was referenced Oct 11, 2025
Merged
Merged
Merged
@noooop noooop changed the title [Model][4/N] Improve all pooling task | Improve enable chunked_prefill & prefix_caching logic. [Model][5/N] Improve all pooling task | Improve enable chunked_prefill & prefix_caching logic. Oct 14, 2025
This was referenced Oct 15, 2025
Open
Merged
Merged
Merged
@noooop noooop changed the title [Model][5/N] Improve all pooling task | Improve enable chunked_prefill & prefix_caching logic. [Model][6/N] Improve all pooling task | Improve enable chunked_prefill & prefix_caching logic. Oct 17, 2025
This was referenced Oct 18, 2025
Open
Merged
@noooop noooop mentioned this pull request Nov 3, 2025
Draft
5 tasks
@noooop noooop mentioned this pull request Nov 10, 2025
Merged
5 tasks
@noooop noooop changed the title [Model][6/N] Improve all pooling task | Improve enable chunked_prefill & prefix_caching logic. [Model][7/N] Improve all pooling task | Improve enable chunked_prefill & prefix_caching logic. Nov 11, 2025
@noooop
init
aa55dab 
Signed-off-by: wang.yuqi <[email protected]>
@noooop noooop force-pushed the chunked_prefill_logic branch from c8e46f4 to aa55dab Compare November 18, 2025 03:37
@noooop noooop changed the title [Model][7/N] Improve all pooling task | Improve enable chunked_prefill & prefix_caching logic. [Model] Improve enable chunked_prefill & prefix_caching logic. Nov 20, 2025
@noooop
fix
0eb45a1 
Signed-off-by: wang.yuqi <[email protected]>
@noooop noooop marked this pull request as ready for review November 20, 2025 10:41
@noooop noooop requested a review from WoosukKwon as a code owner November 20, 2025 10:41
@noooop
Copy link
Collaborator Author

noooop commented Nov 27, 2025 •
edited
Loading

@zhuohan123 @DarkLight1337 @hmellor
Ready for review

@tdoublep
Please help review this PR. This PR is also related to #29393

zhuohan123
zhuohan123 approved these changes Nov 27, 2025
View reviewed changes
Copy link
Member

@zhuohan123 zhuohan123 left a comment

Choose a reason for hiding this comment

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

Thanks for the hard work and the fix!

@DarkLight1337 DarkLight1337 enabled auto-merge (squash) November 27, 2025 09:38
DarkLight1337
DarkLight1337 reviewed Nov 27, 2025
View reviewed changes
@mergify
Copy link

mergify bot commented Nov 27, 2025

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

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 27, 2025
@mergify mergify bot removed the needs-rebase label Nov 27, 2025
@DarkLight1337 DarkLight1337 enabled auto-merge (squash) November 27, 2025 10:04
nwaughachukwuma
nwaughachukwuma reviewed Nov 27, 2025
View reviewed changes
nwaughachukwuma
nwaughachukwuma suggested changes Nov 27, 2025
View reviewed changes
Copy link
Contributor

@nwaughachukwuma nwaughachukwuma left a comment

Choose a reason for hiding this comment

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

Thanks for doing an excellent job here.

However, there're so many not-too-related changes in this PR across multiple touch points. To make reviewing and merging faster, please break this down into multiple PRs, each with relative changes.

Thank you.

@noooop
Copy link
Collaborator Author

noooop commented Nov 27, 2025

However, there're so many not-too-related changes in this PR across multiple touch points. To make reviewing and merging faster, please break this down into multiple PRs, each with relative changes.

Yes, this PR touches many files, but they're all relevant.

@vllm-bot vllm-bot merged commit f4b7605 into vllm-project:main Nov 28, 2025
54 of 56 checks passed
@noooop noooop deleted the chunked_prefill_logic branch November 28, 2025 06:06
kitaekatt pushed a commit to kitaekatt/vllm that referenced this pull request Dec 1, 2025
@noooop @DarkLight1337 @kitaekatt
Improve enable chunked_prefill & prefix_caching logic. (vllm-project#…
9920560 
…26623)

Signed-off-by: wang.yuqi <[email protected]>
Signed-off-by: wang.yuqi <[email protected]>
Co-authored-by: Cyrus Leung <[email protected]>
amd-hhashemi pushed a commit to amd-hhashemi/vllm that referenced this pull request Dec 2, 2025
@noooop @DarkLight1337 @amd-hhashemi
Improve enable chunked_prefill & prefix_caching logic. (vllm-project#…
1347c35 
…26623)

Signed-off-by: wang.yuqi <[email protected]>
Signed-off-by: wang.yuqi <[email protected]>
Co-authored-by: Cyrus Leung <[email protected]>
Signed-off-by: Hashem Hashemi <[email protected]>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@DarkLight1337 DarkLight1337 DarkLight1337 left review comments

@chatgpt-codex-connector chatgpt-codex-connector[bot] chatgpt-codex-connector[bot] left review comments

@zhuohan123 zhuohan123 zhuohan123 approved these changes

@WoosukKwon WoosukKwon Awaiting requested review from WoosukKwon WoosukKwon is a code owner

@youkaichao youkaichao Awaiting requested review from youkaichao youkaichao is a code owner

@robertgshaw2-redhat robertgshaw2-redhat Awaiting requested review from robertgshaw2-redhat robertgshaw2-redhat is a code owner

@mgoin mgoin Awaiting requested review from mgoin mgoin is a code owner

@tlrmchlsmth tlrmchlsmth Awaiting requested review from tlrmchlsmth tlrmchlsmth is a code owner

@houseroad houseroad Awaiting requested review from houseroad houseroad is a code owner

@yewentao256 yewentao256 Awaiting requested review from yewentao256 yewentao256 is a code owner

@ProExpertProg ProExpertProg Awaiting requested review from ProExpertProg ProExpertProg is a code owner

@alexm-redhat alexm-redhat Awaiting requested review from alexm-redhat

@njhill njhill Awaiting requested review from njhill

@heheda12345 heheda12345 Awaiting requested review from heheda12345

@ywang96 ywang96 Awaiting requested review from ywang96

@ApostaC ApostaC Awaiting requested review from ApostaC

@hmellor hmellor Awaiting requested review from hmellor hmellor is a code owner

+1 more reviewer

@nwaughachukwuma nwaughachukwuma nwaughachukwuma requested changes

Reviewers whose approvals may not affect merge requirements

Assignees

No one assigned

Labels

new-model Requests to new models ready ONLY add when PR is ready to merge/full CI is needed v1

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

6 participants

@noooop @DarkLight1337 @zhuohan123 @hmellor @nwaughachukwuma @vllm-bot