[None][fix] Fix AutoDeploy shim test expecting soft fallback for speculative+flashinfer

[achartier]

@coderabbitai summary

Description

test_speculative_flashinfer_fallback_disables_piecewise was failing with a hard pydantic.ValidationError because it was written against the old auto-correction behavior (silent fallback to torch-simple), but the reject_cudagraph_for_speculative_flashinfer validator now explicitly rejects the speculative + FlashInfer + CUDA-graph-backend combination and requires the user to set compile_backend='torch-simple' explicitly.

Fix: pass compile_backend="torch-simple" in the test and rename it to test_speculative_flashinfer_torch_simple_disables_piecewise to accurately describe what it tests. The test still covers a distinct scenario (speculative + flashinfer + torch-simple → piecewise_enabled is False) not exercised by the existing test_accepts_flashinfer_torch_simple or test_non_piecewise_compile_backend_disables_default_piecewise.

Test Coverage

• tests/unittest/auto_deploy/singlegpu/shim/test_llm_config.py::test_speculative_flashinfer_torch_simple_disables_piecewise — the renamed/fixed test itself

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 single test function in the LLM config test suite is renamed and updated to explicitly target the torch-simple compile backend. The test name and backend parameter are synchronized to clarify that piecewise disabling assertions apply to the torch-simple backend scenario in speculative FlashInfer configurations.

Changes

Speculative FlashInfer torch-simple piecewise-disable test update

Layer / File(s)	Summary
Speculative FlashInfer torch-simple piecewise-disable test update tests/unittest/auto_deploy/singlegpu/shim/test_llm_config.py	Test function renamed to test_speculative_flashinfer_torch_simple_disables_piecewise and compile_backend="torch-simple" parameter added to LlmArgs construction, aligning the test name and configuration to explicitly target the torch-simple backend.

Estimated code review effort

🎯 1 (Trivial) | ⏱️ ~3 minutes

Suggested reviewers

• greg-kwasniewski1
• bmarimuthu-nv
• tcherckez-nvidia

🚥 Pre-merge checks | ✅ 4 | ❌ 1

❌ Failed checks (1 warning)

Check name	Status	Explanation	Resolution
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 (4 passed)

Check name	Status	Explanation
Title check	✅ Passed	The title clearly identifies the fix as addressing a test that had incorrect expectations regarding auto-correction behavior for speculative+flashinfer combinations.
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.
Description check	✅ Passed	The PR description is comprehensive and clearly explains the issue, solution, and test coverage with proper checklist completion.

_{✏️ Tip: You can configure your own custom pre-merge checks in the settings.}

✨ Finishing Touches

🧪 Generate unit tests (beta)

• Create PR with unit tests

---

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

[achartier]

/bot run

[tensorrt-cicd]

PR_Github #53727 [ run ] triggered by Bot. Commit: 0a285ff Link to invocation

[tensorrt-cicd]

PR_Github #53727 [ run ] completed with state SUCCESS. Commit: 0a285ff
/LLM/main/L0_MergeRequest_PR pipeline #42855 completed with status: 'SUCCESS'

CI Report

Link to invocation

[achartier]

Addressed by #15293