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.

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

[Model] Replace embedding models with pooling adapter #10769

Merged
merged 25 commits into from
Dec 1, 2024
Merged

[Model] Replace embedding models with pooling adapter #10769

merged 25 commits into from
Dec 1, 2024

Conversation

DarkLight1337
Copy link
Member

@DarkLight1337 DarkLight1337 commented Nov 29, 2024 •
edited
Loading

This PR implements the adapter function in #10674 for embedding models. This function is called at startup time (in get_model_architecture) if --task embedding is passed.

@github-actions GitHub Actions
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.

🚀

@mergify mergify bot added the documentation Improvements or additions to documentation label Nov 29, 2024
@DarkLight1337
Fix lint errors
769507a 
Signed-off-by: DarkLight1337 <[email protected]>
Isotr0py
Isotr0py reviewed Nov 29, 2024
View reviewed changes
vllm/model_executor/models/adapters.py Outdated Show resolved Hide resolved
vllm/model_executor/models/adapters.py Outdated Show resolved Hide resolved
@DarkLight1337
Rename
1d1c7b3 
Signed-off-by: DarkLight1337 <[email protected]>
@DarkLight1337
Split up the condition
666cc19 
Signed-off-by: DarkLight1337 <[email protected]>
@DarkLight1337 DarkLight1337 mentioned this pull request Nov 29, 2024
Open
1 task
@DarkLight1337 DarkLight1337 changed the title [Model] Replace embedding models with generic adapter [Model] Replace embedding models with pooling adapter Nov 29, 2024
@DarkLight1337
Simplify code
ec0fbf7 
Signed-off-by: DarkLight1337 <[email protected]>
@DarkLight1337
Fix typo
8301a08 
Signed-off-by: DarkLight1337 <[email protected]>
Isotr0py
Isotr0py approved these changes Nov 29, 2024
View reviewed changes
Copy link
Collaborator

@Isotr0py Isotr0py left a comment

Choose a reason for hiding this comment

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

Overall LGTM!

@DarkLight1337 DarkLight1337 added the ready ONLY add when PR is ready to merge/full CI is needed label Nov 29, 2024
@DarkLight1337
Remove unused parameter
f52414e 
Signed-off-by: DarkLight1337 <[email protected]>
@DarkLight1337
Fix OOT embedding test
b0e0f14 
Signed-off-by: DarkLight1337 <[email protected]>
@DarkLight1337
Fix config tests
29869a3 
Signed-off-by: DarkLight1337 <[email protected]>
@DarkLight1337
Fix PP tests
12a88ee 
Signed-off-by: DarkLight1337 <[email protected]>
@DarkLight1337
Fix model tests
8c0ed5c 
Signed-off-by: DarkLight1337 <[email protected]>
@DarkLight1337
Fix
fddca25 
Signed-off-by: DarkLight1337 <[email protected]>
@DarkLight1337
Improve auto task selection
cd84a3c 
Signed-off-by: DarkLight1337 <[email protected]>
@DarkLight1337
Revert PP test change to verify auto task selection
5dc0f10 
Signed-off-by: DarkLight1337 <[email protected]>
@DarkLight1337
Fix task selection
bc5f9fb 
Signed-off-by: DarkLight1337 <[email protected]>
@DarkLight1337
Fix registry test
ebffd70 
Signed-off-by: DarkLight1337 <[email protected]>
@DarkLight1337
Fix test grouping
d8ef4ae 
Signed-off-by: DarkLight1337 <[email protected]>
@mergify mergify bot added the ci/build label Nov 30, 2024
@DarkLight1337
Format
3a4d468 
Signed-off-by: DarkLight1337 <[email protected]>
@DarkLight1337
Fix task detection
d4d7ad7 
Signed-off-by: DarkLight1337 <[email protected]>
@DarkLight1337
Fix registry tests
7d8757e 
Signed-off-by: DarkLight1337 <[email protected]>
@mergify Mergify
Copy link

mergify bot commented Nov 30, 2024

This pull request has merge conflicts that must be resolved before it can be
merged. Please rebase the PR, @DarkLight1337.

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 30, 2024
@mergify mergify bot removed the needs-rebase label Nov 30, 2024
@DarkLight1337
Try adding back prefix
7d3631f 
Signed-off-by: DarkLight1337 <[email protected]>
@DarkLight1337
format
69d8d6c 
Signed-off-by: DarkLight1337 <[email protected]>
@DarkLight1337 DarkLight1337 merged commit 1337071 into vllm-project:main Dec 1, 2024
68 checks passed
@DarkLight1337 DarkLight1337 deleted the embedding-adapter branch December 1, 2024 00:02
@DarkLight1337 DarkLight1337 mentioned this pull request Dec 1, 2024
Open
1 task
afeldman-nm pushed a commit to neuralmagic/vllm that referenced this pull request Dec 2, 2024
@DarkLight1337 @afeldman-nm
[Model] Replace embedding models with pooling adapter (vllm-project#1…
cbf1489 
…0769)

Signed-off-by: DarkLight1337 <[email protected]>
Signed-off-by: Andrew Feldman <[email protected]>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@Isotr0py Isotr0py Isotr0py approved these changes

@youkaichao youkaichao Awaiting requested review from youkaichao

@ywang96 ywang96 Awaiting requested review from ywang96 ywang96 is a code owner

Assignees
No one assigned
Labels
ci/build documentation Improvements or additions to documentation ready ONLY add when PR is ready to merge/full CI is needed
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
2 participants
@DarkLight1337 @Isotr0py