test: Enforce max_inflight_requests as a global per-step limit across ensemble requests

[pskiran1]

What does the PR do?

Updates the L0 simple ensemble QA tests to validate that max_inflight_requests behaves as a global per-step limit when multiple ensemble requests and multi-step pipelines are involved.

Changes:

• Refactors qa/L0_simple_ensemble/test.sh to build dedicated model repositories for max-queue-size step testing and for multi-step backpressure (max_inflight_requests) scenarios, and to improve failure logging.
• Reworks qa/L0_simple_ensemble/ensemble_backpressure_test.py to add concurrent, sequential, and cancellation scenarios across multiple max_inflight_requests configurations, and adds optional batched-input shaping for the new ensemble models.

Checklist

• PR title reflects the change and is of format <commit_type>: <Title>
• Changes are described in the pull request.
• Related issues are referenced.
• Populated github labels field
• Added test plan and verified test passes.
• Verified that the PR passes existing CI.
• Verified copyright is correct on all changed files.
• Added succinct git squash message before merging ref.
• All template sections are filled out.
• Optional: Additional screenshots for behavior/output changes with before/after.

Commit Type:

Check the conventional commit type
box here and add the label to the github PR.

• build
• ci
• docs
• feat
• fix
• perf
• refactor
• revert
• style
• test

Related PRs:

• feat: Enforce max_inflight_requests as a global per-step limit across ensemble requests core#482
• doc: Enforce max_inflight_requests as a global per-step limit across ensemble requests common#152

Where should the reviewer start?

Test plan:

• CI Pipeline ID:

Caveats:

Background

Related Issues: (use one of the action keywords Closes / Fixes / Resolves / Relates to)

• closes GitHub issue: max_inflight_requests functionality for whole ensemble (rather than per-request) #8597

[Copilot]

Pull request overview

Updates the L0 simple ensemble QA tests to validate that max_inflight_requests behaves as a global per-step limit when multiple ensemble requests and multi-step pipelines are involved.

Changes:

• Refactors qa/L0_simple_ensemble/test.sh to build dedicated model repositories for max-queue-size step testing and for multi-step backpressure (max_inflight_requests) scenarios, and to improve failure logging.
• Reworks qa/L0_simple_ensemble/ensemble_backpressure_test.py to add concurrent, sequential, and cancellation scenarios across multiple max_inflight_requests configurations, and adds optional batched-input shaping for the new ensemble models.

Reviewed changes

Copilot reviewed 2 out of 2 changed files in this pull request and generated 1 comment.

File	Description
qa/L0_simple_ensemble/test.sh	Builds new model repos for the updated backpressure tests and adjusts test execution / expected counts.
qa/L0_simple_ensemble/ensemble_backpressure_test.py	Adds new backpressure test cases and changes request tensor shaping for batched ensemble configs.

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

You can also share your feedback on Copilot code review. Take the survey.