[https://nvbugs/6240561][fix] Unwaive DeepSeek R1 accuracy test

[taylor-yb-lee]

Summary by CodeRabbit

• Tests
  • Reactivated a previously waived integration test case for validation.

Description

In #14793 DR1 accuracy restored to 95

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.

[taylor-yb-lee]

/bot run --disable-fail-fast --extra-stage "DGX_B200-8_GPUs-AutoDeploy-Post-Merge-1"

[coderabbitai]

📝 Walkthrough

Walkthrough

This PR removes a single waived integration test case from tests/integration/test_lists/waives.txt. The waived test TestModelRegistryAccuracy::test_autodeploy_from_registry[deepseek-ai_DeepSeek-R1-0528-True] is deleted from the waiver list, re-enabling that specific parameterized test for execution.

Changes

Test Waiver Update

Layer / File(s)	Summary
Remove waived test case tests/integration/test_lists/waives.txt	The waiver entry for accuracy/test_llm_api_autodeploy.py::TestModelRegistryAccuracy::test_autodeploy_from_registry[deepseek-ai_DeepSeek-R1-0528-True] is removed, allowing that test case to run.

Estimated code review effort

🎯 1 (Trivial) | ⏱️ ~2 minutes

Possibly related PRs

• NVIDIA/TensorRT-LLM#14783: Edits the same waiver file to adjust DeepSeek and other test case exemptions.
• NVIDIA/TensorRT-LLM#14700: Modifies the same waiver file to reenable previously skipped auto-deploy test cases.
• NVIDIA/TensorRT-LLM#14789: Modifies the same waiver file, affecting the same test autodeploy cases.

Suggested reviewers

• MrGeva
• suyoggupta

🚥 Pre-merge checks | ✅ 4 | ❌ 1

❌ Failed checks (1 warning)

Check name	Status	Explanation	Resolution
Description check	⚠️ Warning	The PR description is incomplete. It lacks a proper title following the required format and provides minimal context in the Description section.	Add a properly formatted title like '[https://nvbugs/6240561][fix] Unwaive DeepSeek R1 accuracy test' and expand the Description section with clear explanation of why the test is being unwaived and what validation confirms it's now passing.

✅ Passed checks (4 passed)

Check name	Status	Explanation
Title check	✅ Passed	The title clearly references the NVBugs ticket and describes the main change: removing a waived DeepSeek R1 accuracy test from the waiver list.
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.

_{✏️ 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.}

[tensorrt-cicd]

PR_Github #51651 [ run ] triggered by Bot. Commit: 8d657ab Link to invocation

[taylor-yb-lee]

/bot kill

[taylor-yb-lee]

/bot run --disable-fail-fast --stage-list "DGX_B200-8_GPUs-AutoDeploy-Post-Merge-1"

[tensorrt-cicd]

PR_Github #51660 [ run ] triggered by Bot. Commit: 8d657ab Link to invocation

[tensorrt-cicd]

PR_Github #51661 [ kill ] triggered by Bot. Commit: 8d657ab Link to invocation

[tensorrt-cicd]

PR_Github #51651 [ run ] completed with state ABORTED. Commit: 8d657ab

Link to invocation

[tensorrt-cicd]

PR_Github #51660 [ run ] completed with state ABORTED. Commit: 8d657ab

Link to invocation

[tensorrt-cicd]

PR_Github #51661 [ kill ] completed with state SUCCESS. Commit: 8d657ab
Successfully killed previous jobs for commit 8d657ab

Link to invocation

[taylor-yb-lee]

/bot run --disable-fail-fast --stage-list "DGX_B200-8_GPUs-AutoDeploy-Post-Merge-1"

[tensorrt-cicd]

PR_Github #51663 [ run ] triggered by Bot. Commit: 8d657ab Link to invocation

[tensorrt-cicd]

PR_Github #51663 [ run ] completed with state SUCCESS. Commit: 8d657ab
/LLM/main/L0_MergeRequest_PR pipeline #41045 (Partly Tested) completed with status: 'SUCCESS'

CI Report

Link to invocation

[taylor-yb-lee]

/bot skip --comment "[2026-06-02T19:59:40.143Z] DGX_B200-8_GPUs-AutoDeploy-Post-Merge-1/accuracy/test_llm_api_autodeploy.py::TestModelRegistryAccuracy::test_autodeploy_from_registry[deepseek-ai_DeepSeek-R1-0528-True] <- accuracy/test_llm_api_autodeploy.py PASSED"

[tensorrt-cicd]

PR_Github #51694 [ skip ] triggered by Bot. Commit: 8d657ab Link to invocation

[tensorrt-cicd]

PR_Github #51694 [ skip ] completed with state SUCCESS. Commit: 8d657ab
Skipping testing for commit 8d657ab

Link to invocation