test: Resolve L0_backend_python test flakiness issues#8830
Merged
pskiran1 merged 19 commits intoJun 16, 2026
Conversation
… of https://github.com/triton-inference-server/server into spolisetty/tri-1315-fix-ci-test-l0_backend_python-base
Vinya567
approved these changes
Jun 15, 2026
yinggeh
approved these changes
Jun 16, 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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?
OUTPUT0toOUTto match the model config.tearDown()to always close the gRPC stream and client, preventing indefinite hangs when a test assertion fails beforestop_stream().execute_delayfrom4sto10sintest_decoupled_execute_cancel. The prior1smargin between the model's first loop iteration and client cancellation was insufficient on loaded CI machines./dev/shm/triton_python_backend_shm_region_*files at before test starts. (2) Filter stale regions in the 4MB size-validation loop so only regions from the current server are checked.python_backendand theinstance_kindexample, which downloads from GitHub at runtime and is prone to transient504/timeouterrors.test_load_with_file_overrideto acceptUnicodeDecodeErroralongsideTritonModelExceptionfor the expected-failure path, since binary ONNX data occasionally triggers apybind11decode error at the bytes→string boundary. Additionally updated is model ready validation.Checklist
<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/python_backend#439
Where should the reviewer start?
Test plan:
Caveats:
Background
Related Issues: (use one of the action keywords Closes / Fixes / Resolves / Relates to)