ci: Ensemble requests stuck indefinitely when the step max_queue_size exceeded - #8631
Merged
pskiran1 merged 7 commits intoFeb 11, 2026
Conversation
pskiran1
changed the title
max_queue_size exceeded
Contributor
There was a problem hiding this comment.
Pull request overview
This PR addresses a critical issue where ensemble requests could become stuck indefinitely when a step's max_queue_size was exceeded. The fix ensures proper error handling and stream termination when queue limits are reached.
Changes:
- Added comprehensive test coverage for
max_queue_sizebehavior in ensemble steps - Updated existing backpressure tests to properly handle and verify error responses
- Modified the decoupled producer model to support batching and introduce processing delays
Reviewed changes
Copilot reviewed 4 out of 4 changed files in this pull request and generated 2 comments.
| File | Description |
|---|---|
| qa/L0_simple_ensemble/test.sh | Added new test section for max_queue_size in ensemble steps with two scenarios (step1 and step2) |
| qa/L0_simple_ensemble/ensemble_backpressure_test.py | Refactored response collection to handle errors, added new test class for max_queue_size validation |
| qa/L0_simple_ensemble/backpressure_test_models/decoupled_producer/config.pbtxt | Enabled batching by changing max_batch_size from 0 to 1 |
| qa/L0_simple_ensemble/backpressure_test_models/decoupled_producer/1/model.py | Added processing delay and fixed tensor shape handling |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
…-when-using-dynamic-batcher
yinggeh
approved these changes
Feb 9, 2026
…-dynamic-batcher' of https://github.com/triton-inference-server/server into spolisetty/tri-654-bug-in-ensemble-scheduler-when-using-dynamic-batcher
pskiran1
deleted the
spolisetty/tri-654-bug-in-ensemble-scheduler-when-using-dynamic-batcher
branch
February 11, 2026 17:37
pskiran1
added a commit
that referenced
this pull request
Feb 13, 2026
mc-nv
pushed a commit
that referenced
this pull request
Feb 13, 2026
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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.
What does the PR do?
Test coverage for triton-inference-server/core#466
Changes:
max_queue_sizebehavior in ensemble stepsChecklist
<commit_type>: <Title>Commit Type:
Check the conventional commit type
box here and add the label to the github PR.
Related PRs:
triton-inference-server/core#466
Where should the reviewer start?
Test plan:
Caveats:
Background
Related Issues: (use one of the action keywords Closes / Fixes / Resolves / Relates to)