[https://nvbugs/6309375][test] AutoDeploy: Remove stale fallback test

[govind-ramnarayan]

FlashInfer attention with speculative decoding and CUDA graph backends is now rejected by AutoDeploy LlmArgs validation. The deleted test asserted the older fallback behavior, which contradicts the current contract and is already covered by TestSpeculativeConfigValidation::test_rejects_flashinfer_cuda_graph_backend for torch-cudagraph and torch-opt.

Drop the matching waive because no skipped test remains for this NVBug.

Summary by CodeRabbit

• Tests
  • Removed a previously skipped test case and its corresponding waiver entry.

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

Removes the test_speculative_flashinfer_fallback_disables_piecewise test unit test and its corresponding waiver entry. The test validated that speculative decoding with flashinfer backend forced torch-simple compilation and disabled piecewise transforms.

Changes

Test and Waiver Removal

Layer / File(s)	Summary
Remove waived test and cleanup tests/unittest/auto_deploy/singlegpu/shim/test_llm_config.py, tests/integration/test_lists/waives.txt	Deleted the test_speculative_flashinfer_fallback_disables_piecewise test that verified compilation backend enforcement with flashinfer attention, and removed its skip waiver entry from the waiver list.

Estimated code review effort

🎯 1 (Trivial) | ⏱️ ~2 minutes

Possibly related PRs

• NVIDIA/TensorRT-LLM#15293: Directly conflicts by adding the same test waiver entry that this PR removes.
• NVIDIA/TensorRT-LLM#15061: Also removes the waiver for the same test under NVBUG 6162120 as part of a broader waiver cleanup.

Suggested reviewers

• nvchenghaoz
• dpitman-nvda
• tburt-nv

🚥 Pre-merge checks | ✅ 4 | ❌ 1

❌ Failed checks (1 inconclusive)

Check name	Status	Explanation	Resolution
Description check	❓ Inconclusive	PR description clearly explains the changes, rationale, and references the NVBug. However, the actual sections (Description and Test Coverage) within the template are not filled out with details.	Fill in the 'Description' section with the explanation provided above the template, and add 'Test Coverage' section detailing how TestSpeculativeConfigValidation::test_rejects_flashinfer_cuda_graph_backend covers the removed test.

✅ Passed checks (4 passed)

Check name	Status	Explanation
Docstring Coverage	✅ Passed	No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check.
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.
Title check	✅ Passed	The title clearly and concisely describes the main change: removing a stale fallback test from AutoDeploy, with the NVBug reference providing context.

_{✏️ 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.}

[govind-ramnarayan]

/bot run --disable-fail-fast

[tensorrt-cicd]

PR_Github #53937 [ run ] triggered by Bot. Commit: adf65d6 Link to invocation

[tensorrt-cicd]

PR_Github #53937 [ run ] completed with state SUCCESS. Commit: adf65d6
/LLM/main/L0_MergeRequest_PR pipeline #43028 completed with status: 'SUCCESS'

CI Report

Link to invocation