[https://nvbugs/6094208][fix] AutoDeploy: skip bf16 Nemotron-Nano-V3 accuracy test on <80GB GPUs

[galagam]

Summary by CodeRabbit

• Tests
  • Updated test configuration to improve resource handling for specific model variants.

Description

The Nano 30B bf16 weights alone nearly exceed the memory available on L40-class cards, so the test OOMs in CI even with low-memory overrides applied. Gate the bf16 parametrize entry on >=80GB device memory; fp8/nvfp4 remain gated by their existing architecture markers.

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]

No actionable comments were generated in the recent review. 🎉

ℹ️ Recent review info

⚙️ Run configuration

Configuration used: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Enterprise

Run ID: 05e99335-c56a-44a3-a870-f4980cb830e2

📥 Commits

Reviewing files that changed from the base of the PR and between bd54511 and 3c28a87.

📒 Files selected for processing (1)

• tests/integration/defs/accuracy/test_llm_api_autodeploy.py

---

📝 Walkthrough

Walkthrough

A single test parameter in the Nemotron accuracy test is updated to include a conditional skip mark. The "bf16" model variant now skips execution on machines with insufficient device memory (less than 80000), replacing an unmarked plain parameter entry.

Changes

Test skip condition for Nemotron bf16 model

Layer / File(s)	Summary
Nemotron bf16 model test skip mark tests/integration/defs/accuracy/test_llm_api_autodeploy.py	The "bf16" entry in TestNemotronNanoV3.test_accuracy parametrization is wrapped in pytest.param with skip_less_device_memory(80000) to conditionally skip on machines with less than 80000 device memory.

Estimated code review effort

🎯 1 (Trivial) | ⏱️ ~3 minutes

Possibly related PRs

• NVIDIA/TensorRT-LLM#13846: Also modifies test skip conditions and parametrization logic in the same AutoDeploy accuracy test file based on device memory constraints.

Suggested reviewers

• lucaslie
• MrGeva

🚥 Pre-merge checks | ✅ 5

✅ Passed checks (5 passed)

Check name	Status	Explanation
Title check	✅ Passed	The title clearly and specifically describes the main change: adding a memory threshold skip condition for the bf16 Nemotron-Nano-V3 accuracy test. It references the bug ID, type, and the concrete condition (<80GB GPUs).
Description check	✅ Passed	The PR description clearly explains the issue (Nano 30B bf16 weights cause OOM on L40-class cards) and the solution (gate test on >=80GB device memory). However, the Test Coverage section is incomplete with placeholder comment only.
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.}

[galagam]

/bot run

[tensorrt-cicd]

PR_Github #48885 [ run ] triggered by Bot. Commit: 3c28a87 Link to invocation

[tensorrt-cicd]

PR_Github #48885 [ run ] completed with state SUCCESS. Commit: 3c28a87
/LLM/main/L0_MergeRequest_PR pipeline #38635 completed with status: 'SUCCESS'

CI Report

Link to invocation