Skip to content

[V1] Remove input cache client #14864

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 8 commits into from
Mar 17, 2025
Merged

[V1] Remove input cache client #14864

merged 8 commits into from
Mar 17, 2025

Conversation

DarkLight1337
Copy link
Member

All multi-modal models that support V1 have been refactored to use the merged input processor, so we can remove the code path that corresponds to legacy input mapper.

@DarkLight1337 DarkLight1337 requested a review from ywang96 March 15, 2025 14:03
@github-actions GitHub Actions
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.

🚀

@DarkLight1337 DarkLight1337 mentioned this pull request Mar 15, 2025
Open
53 tasks
@mergify mergify bot added the v1 label Mar 15, 2025
@DarkLight1337 DarkLight1337 added multi-modality Related to multi-modality (#4194) ready ONLY add when PR is ready to merge/full CI is needed labels Mar 15, 2025
@DarkLight1337
Add informative error message
2a88876 
Signed-off-by: DarkLight1337 <[email protected]>
@DarkLight1337 DarkLight1337 moved this to In Progress in Multi-modality Core Mar 15, 2025
@DarkLight1337 DarkLight1337 self-assigned this Mar 15, 2025
@DarkLight1337 DarkLight1337 changed the title [VLM][V1] Remove input cache client [V1] Remove input cache client Mar 15, 2025
@DarkLight1337
Merge branch 'main' into deprecate-mm-cache-client
7554e6e 
Signed-off-by: DarkLight1337 <[email protected]>
@DarkLight1337
Fix
f7cea21 
Signed-off-by: DarkLight1337 <[email protected]>
@vllm-project vllm-project deleted a comment from DarkLight1337 Mar 17, 2025
@ywang96
Copy link
Member

ywang96 commented Mar 17, 2025

Ooops - I deleted a comment by accident - but yes we only need to consider models that are supported on V1.

ywang96
ywang96 approved these changes Mar 17, 2025
View reviewed changes
Copy link
Member

@ywang96 ywang96 left a comment •
edited
Loading

Choose a reason for hiding this comment

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

LGTM! I added a few changes for better code clarity and fixed the CI errors

@ywang96
update
45c558f 
Signed-off-by: Roger Wang <[email protected]>
@DarkLight1337 DarkLight1337 enabled auto-merge (squash) March 17, 2025 05:16
@vllm-bot vllm-bot merged commit b539222 into vllm-project:main Mar 17, 2025
29 of 31 checks passed
@github-project-automation github-project-automation bot moved this from In Progress to Done in Multi-modality Core Mar 17, 2025
@DarkLight1337 DarkLight1337 deleted the deprecate-mm-cache-client branch March 17, 2025 07:00
@DarkLight1337 DarkLight1337 mentioned this pull request Mar 26, 2025
Closed
57 tasks
lulmer pushed a commit to lulmer/vllm that referenced this pull request Apr 7, 2025
@DarkLight1337 @ywang96 @lulmer
[V1] Remove input cache client (vllm-project#14864)
0421aa8 
Signed-off-by: DarkLight1337 <[email protected]>
Signed-off-by: Roger Wang <[email protected]>
Co-authored-by: Roger Wang <[email protected]>
Signed-off-by: Louis Ulmer <[email protected]>
@DarkLight1337 DarkLight1337 mentioned this pull request Apr 8, 2025
Merged
@ckhordiasma ckhordiasma mentioned this pull request Apr 17, 2025
Closed
shreyankg pushed a commit to shreyankg/vllm that referenced this pull request May 3, 2025
@DarkLight1337 @ywang96 @shreyankg
[V1] Remove input cache client (vllm-project#14864)
c3c3452 
Signed-off-by: DarkLight1337 <[email protected]>
Signed-off-by: Roger Wang <[email protected]>
Co-authored-by: Roger Wang <[email protected]>
RichardoMrMu pushed a commit to RichardoMrMu/vllm that referenced this pull request May 12, 2025
@DarkLight1337 @ywang96
[V1] Remove input cache client (vllm-project#14864)
cae87df 
Signed-off-by: DarkLight1337 <[email protected]>
Signed-off-by: Roger Wang <[email protected]>
Co-authored-by: Roger Wang <[email protected]>
Signed-off-by: Mu Huai <[email protected]>
@lgeiger lgeiger mentioned this pull request Jun 10, 2025
Merged
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@ywang96 ywang96 ywang96 approved these changes

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

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

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

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

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

Assignees

@DarkLight1337 DarkLight1337

@ywang96 ywang96

Labels
multi-modality Related to multi-modality (#4194) ready ONLY add when PR is ready to merge/full CI is needed v1
Projects
Multi-modality Core
Status: Done
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
3 participants
@DarkLight1337 @ywang96 @vllm-bot