[RemoteModels] OpenAI batch Support #9156
Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# Conflicts: # tests/serving/test_async_flow.py
# Conflicts: # tests/serving/test_async_flow.py
update test to use v2modelserver as model_mode and not as None
add simpler test: test_monitoring_with_model_runner_batch_infer
gtopper
reviewed
Jan 8, 2026
gtopper
reviewed
Jan 8, 2026
royischoss
reviewed
Jan 8, 2026
Contributor
royischoss
left a comment
There was a problem hiding this comment.
Hey looks good some comments
royischoss
reviewed
Jan 8, 2026
gtopper
reviewed
Jan 13, 2026
gtopper
reviewed
Jan 13, 2026
1d3c600 to
33ef902
Compare
10 tasks
davesh0812
reviewed
Jan 14, 2026
davesh0812
reviewed
Jan 14, 2026
tomerm-iguazio
commented
Jan 15, 2026
davesh0812
approved these changes
Jan 15, 2026
Contributor
davesh0812
left a comment
There was a problem hiding this comment.
LGTM,
one comment for followup pr
| try: | ||
| # gather() stops on first exception - fast fail | ||
| return await asyncio.gather(*tasks) | ||
| except: |
Contributor
There was a problem hiding this comment.
please add relevant list of exceptions here
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
4 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
📝 Description
Added support for OpenAI batch processing, including asynchronous batch execution.
Added integration and unit tests.
Depend on #9117
🛠️ Changes Made
Added batch invocation support (sync via
ThreadPoolExecutor, async viaasyncio.gather) with two-level concurrency control: (1) instance-level thread pool (_executor) for sync batches with per-batch semaphore limiting concurrent threads, and (2) class-level global async semaphore (_global_async_semaphore) shared across all instances to enforce total async request limits while per-batch semaphores ensure fair distribution-preventing API rate limit violations and resource monopolization.✅ Checklist
🧪 Testing
🔗 References
🚨 Breaking Changes?
🔍️ Additional Notes