[TRTLLM-13446][test] Add FLUX infer() num_images_per_prompt forwardin…

[yingguo-trt]

…g test

The existing GPU tests call forward() directly, so a regression where infer() drops num_images_per_prompt (the original TRTLLM-12870 failure mode) would still pass. Add a CPU-only stubbed test that asserts infer() forwards the parameter to forward(), parametrized over FluxPipeline and Flux2Pipeline. Register in l0_a10.

Summary by CodeRabbit

• Tests
  • Added coverage for image-generation request handling across multiple pipeline variants.
  • Verified that inference returns the pipeline’s direct output and correctly passes through the number of images requested per prompt.

Description

Test Coverage

PR Checklist

Please review the following before submitting your PR:

• PR description clearly explains what and why. If using CodeRabbit's summary, please make sure it makes sense.

• PR Follows TRT-LLM CODING GUIDELINES to the best of your knowledge.

• Test cases are provided for new code paths (see test instructions)

• If PR introduces API changes, an appropriate PR label is added - either api-compatible or api-breaking. For api-breaking, include BREAKING in the PR title.

• Any new dependencies have been scanned for license and vulnerabilities

• CODEOWNERS updated if ownership changes

• Documentation updated as needed

• Update tava architecture diagram if there is a significant design change in PR.

• The reviewers assigned automatically/manually are appropriate for the PR.

• Please check this after reviewing the above items as appropriate for this PR.

GitHub Bot Help

To see a list of available CI bot commands, please comment /bot help.

[coderabbitai]

📝 Walkthrough

Walkthrough

A new unit test file tests/unittest/_torch/visual_gen/test_flux_infer.py is added, containing a parametrized test for FluxPipeline and Flux2Pipeline that verifies infer returns the forward mock value and passes num_images_per_prompt as a keyword argument. The test is registered in tests/integration/test_lists/test-db/l0_a10.yml.

Changes

FLUX Pipeline Infer Unit Test

Layer / File(s)	Summary
FluxPipeline infer test and CI registration tests/unittest/_torch/visual_gen/test_flux_infer.py, tests/integration/test_lists/test-db/l0_a10.yml	Adds parametrized test asserting infer returns forward's value and forwards num_images_per_prompt; registers the test in the l0_a10 CI list.

Estimated code review effort

🎯 1 (Trivial) | ⏱️ ~3 minutes

🚥 Pre-merge checks | ✅ 3 | ❌ 2

❌ Failed checks (2 warnings)

Check name	Status	Explanation	Resolution
Description check	⚠️ Warning	The description explains the fix, but the required Test Coverage and PR Checklist sections are left unfilled.	Add a Test Coverage section and complete the PR Checklist with the required confirmations before merging.
Docstring Coverage	⚠️ Warning	Docstring coverage is 0.00% which is insufficient. The required threshold is 80.00%.	Write docstrings for the functions missing them to satisfy the coverage threshold.

✅ Passed checks (3 passed)

Check name	Status	Explanation
Title check	✅ Passed	The title matches the main change and includes a valid ticket prefix, with the truncation still leaving the FLUX infer() test intent clear.
Linked Issues check	✅ Passed	Check skipped because no linked issues were found for this pull request.
Out of Scope Changes check	✅ Passed	Check skipped because no linked issues were found for this pull request.

✨ Finishing Touches

🧪 Generate unit tests (beta)

• Create PR with unit tests

---

_{Comment @coderabbitai help to get the list of available commands.}

[coderabbitai]

Actionable comments posted: 1

🤖 Prompt for all review comments with AI agents

Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

Inline comments:
In `@tests/unittest/_torch/visual_gen/test_flux_infer.py`:
- Around line 1-2: The new test file currently has only the SPDX header, but new
Python source files must include the repository-mandated NVIDIA copyright block.
Update the header in the test file to use the standard NVIDIA source copyright
header required for all new .py files, keeping the SPDX license line if needed,
and ensure the file begins with the full NVIDIA copyright notice used elsewhere
in the repo.

🪄 Autofix (Beta)

Fix all unresolved CodeRabbit comments on this PR:

• Push a commit to this branch (recommended)
• Create a new PR with the fixes

---

ℹ️ Review info

⚙️ Run configuration

Configuration used: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Enterprise

Run ID: 56f02e74-ea75-406d-a28b-b06415d5c97c

📥 Commits

Reviewing files that changed from the base of the PR and between a9f5fc7 and fdc2006.

📒 Files selected for processing (2)

• tests/integration/test_lists/test-db/l0_a10.yml
• tests/unittest/_torch/visual_gen/test_flux_infer.py

[yingguo-trt]

/bot run

[yingguo-trt]

/bot run

[yingguo-trt]

/bot run

[yingguo-trt]

/bot run

[yingguo-trt]

/bot run

[tensorrt-cicd]

PR_Github #57376 [ run ] triggered by Bot. Commit: 379fed7 Link to invocation

[yingguo-trt]

/bot run

[tensorrt-cicd]

PR_Github #57379 [ run ] triggered by Bot. Commit: 379fed7 Link to invocation

[tensorrt-cicd]

PR_Github #57376 [ run ] completed with state ABORTED. Commit: 379fed7

Link to invocation

[tensorrt-cicd]

PR_Github #57379 [ run ] completed with state SUCCESS. Commit: 379fed7
/LLM/main/L0_MergeRequest_PR pipeline #46128 completed with status: 'SUCCESS'

CI Report

Link to invocation