[https://nvbugs/6143879][fix] add a fixed random seed for the test

[nvchenghaoz]

Ran the test 40 times locally and cannot reproduce the error. Add a fixed random seed for the test.

Summary by CodeRabbit

• Tests
  • Enhanced determinism in FP8 BMM quantization tests for more reliable test execution.

[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: 4bf510ca-8be6-49a7-8b51-579d48eda458

📥 Commits

Reviewing files that changed from the base of the PR and between 2f79ebb and 7c03e55.

📒 Files selected for processing (1)

• tests/unittest/auto_deploy/singlegpu/transformations/library/test_quantization.py

---

📝 Walkthrough

Walkthrough

This PR adds deterministic random seeding to the test_bmm_quantization test function via torch.manual_seed(0). The seed is set before model dimensions and input construction, ensuring reproducible results for FP8 BMM quantization tests without changing any quantization logic, transforms, or assertions.

Changes

Test Determinism

Layer / File(s)	Summary
Test Seed Setup tests/unittest/auto_deploy/singlegpu/transformations/library/test_quantization.py	torch.manual_seed(0) added at the start of test_bmm_quantization to ensure deterministic model and input generation.

---

🎯 1 (Trivial) | ⏱️ ~2 minutes

🚥 Pre-merge checks | ✅ 3 | ❌ 2

❌ Failed checks (2 warnings)

Check name	Status	Explanation	Resolution
Description check	⚠️ Warning	The description is minimal and lacks required sections like detailed explanation of the issue, test coverage details, and PR checklist items specified in the template.	Expand the description to include: (1) detailed explanation of why the random seed is needed, (2) which test cases validate this fix, and (3) completion of the PR checklist with explicit checkboxes.
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 clearly identifies the fix and the purpose: adding a fixed random seed for a test to address a specific bug.
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.}

[nvchenghaoz]

/bot run --stage-list "A10-Build_Docs, A10-PackageSanityCheck-PY310-UB2204, A100X-PackageSanityCheck-PY312-UB2404, A30-AutoDeploy-1, H100_PCIe-AutoDeploy-1, DGX_B200-AutoDeploy-1, A100X-PyTorch-1"

[tensorrt-cicd]

PR_Github #47231 [ run ] triggered by Bot. Commit: 9707c21 Link to invocation

[tensorrt-cicd]

PR_Github #47231 [ run ] completed with state SUCCESS. Commit: 9707c21
/LLM/main/L0_MergeRequest_PR pipeline #37187 (Partly Tested) completed with status: 'SUCCESS'

CI Report

Link to invocation

[nvchenghaoz]

/bot skip --comment "Fix AutoDeploy unit test, since the AutoDeploy unit test passed, skip the whole pipeline"

[tensorrt-cicd]

PR_Github #47253 [ skip ] triggered by Bot. Commit: 9707c21 Link to invocation

[tensorrt-cicd]

PR_Github #47253 [ skip ] completed with state SUCCESS. Commit: 9707c21
Skipping testing for commit 9707c21

Link to invocation