[https://nvbugs/6080024][fix] Fix CudaGraphConfig validation conflict from YAML deep merge

[nvchenghaoz]

Summary by CodeRabbit

• Chores

  • Updated CUDA graph configuration settings for model deployment.

• Tests

  • Modified test execution scheduling for GPU environments.
  • Disabled a test case for a specific model configuration.

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)

• 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.

[nvchenghaoz]

/bot run --extra-stage "DGX_B200-4_GPUs-AutoDeploy-1, DGX_H100-4_GPUs-AutoDeploy-1"

[coderabbitai]

📝 Walkthrough

Walkthrough

Two configuration updates are made: CUDA graph batch size alignment in a model registry configuration file, and test execution scheduling adjustment with a specific test case disabled in integration test configurations.

Changes

Cohort / File(s)	Summary
Model Configuration Updates examples/auto_deploy/model_registry/configs/qwen3.5_moe_400b.yaml	Sets cuda_graph_config.max_batch_size to 256 to align with top-level batch size configuration.
Test Configuration Updates tests/integration/test_lists/test-db/l0_dgx_b200.yml	Changes autodeploy/mpi execution stage from post_merge to pre_merge for 8-GPU b200 environment; disables TestModelRegistryAccuracy::test_autodeploy_from_registry test for deepseek-ai_DeepSeek-R1-0528-True variant.

Estimated code review effort

🎯 2 (Simple) | ⏱️ ~10 minutes

🚥 Pre-merge checks | ✅ 4 | ❌ 1

❌ Failed checks (1 warning)

Check name	Status	Explanation	Resolution
Description check	⚠️ Warning	PR description is completely unfilled; only the template structure remains with no actual content explaining the changes, rationale, or test coverage.	Fill in the Description section explaining the CudaGraphConfig validation conflict and why the YAML changes fix it. Add Test Coverage section listing affected tests. Complete the PR Checklist items.

✅ Passed checks (4 passed)

Check name	Status	Explanation
Title check	✅ Passed	The title clearly specifies the issue (CudaGraphConfig validation conflict from YAML deep merge) and the fix, directly corresponding to changes in the qwen3.5_moe_400b.yaml configuration file.
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

Tip

💬 Introducing Slack Agent: The best way for teams to turn conversations into code.

Slack Agent is built on CodeRabbit's deep understanding of your code, so your team can collaborate across the entire SDLC without losing context.

• Generate code and open pull requests
• Plan features and break down work
• Investigate incidents and troubleshoot customer tickets together
• Automate recurring tasks and respond to alerts with triggers
• Summarize progress and report instantly

Built for teams:

• Shared memory across your entire org—no repeating context
• Per-thread sandboxes to safely plan and execute work
• Governance built-in—scoped access, auditability, and budget controls

One agent for your entire SDLC. Right inside Slack.

👉 Get started

---

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

[coderabbitai]

Actionable comments posted: 2

🤖 Prompt for all review comments with AI agents

Verify each finding against the current code and only fix it if needed.

Inline comments:
In `@tests/integration/test_lists/test-db/l0_dgx_b200.yml`:
- Line 376: The test
TestModelRegistryAccuracy::test_autodeploy_from_registry[deepseek-ai_DeepSeek-R1-0528-True]
was silently commented out; either re-enable it in the appropriate test stage or
quarantine it explicitly: if re-enabling, remove the comment so the test runs;
if quarantining, replace the commented entry with a quarantine record that
includes required metadata (nvbug/id, owner, target_reenable_date, and a short
reason) so the omission is tracked and automatically reviewable.
- Line 371: The section header "AutoDeploy Post Merge 8 GPU tests" and the stage
key "stage: pre_merge" are inconsistent; update either the header text to
"AutoDeploy Pre Merge 8 GPU tests" or change the stage value to "post_merge" so
the section label and the stage key match (look for the header string
"AutoDeploy Post Merge 8 GPU tests" and the YAML key "stage" in that block to
make the edit).

🪄 Autofix (Beta)

Fix all unresolved CodeRabbit comments on this PR:

• Push a commit to this branch (recommended)
• Create a new PR with the fixes

---

ℹ️ Review info

⚙️ Run configuration

Configuration used: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Enterprise

Run ID: c0505814-4372-493c-81af-4ce5476d2bcd

📥 Commits

Reviewing files that changed from the base of the PR and between 79396d8 and 2968943.

📒 Files selected for processing (2)

• examples/auto_deploy/model_registry/configs/qwen3.5_moe_400b.yaml
• tests/integration/test_lists/test-db/l0_dgx_b200.yml

[tensorrt-cicd]

PR_Github #45251 [ run ] triggered by Bot. Commit: 2968943 Link to invocation

[tensorrt-cicd]

PR_Github #45251 [ run ] completed with state SUCCESS. Commit: 2968943
/LLM/main/L0_MergeRequest_PR pipeline #35510 completed with status: 'FAILURE'

CI Report

⚠️ Action Required:

• Please check the failed tests and fix your PR
• If you cannot view the failures, ask the CI triggerer to share details
• Once fixed, request an NVIDIA team member to trigger CI again

Link to invocation

[nvchenghaoz]

/bot run --extra-stage "DGX_B200-4_GPUs-AutoDeploy-1, DGX_H100-4_GPUs-AutoDeploy-1"

[tensorrt-cicd]

PR_Github #46684 [ run ] triggered by Bot. Commit: 3ba1341 Link to invocation

[nvchenghaoz]

/bot run --stage-list "DGX_B200-4_GPUs-AutoDeploy-1"

[tensorrt-cicd]

PR_Github #46684 [ run ] completed with state SUCCESS. Commit: 3ba1341
/LLM/main/L0_MergeRequest_PR pipeline #36723 completed with status: 'FAILURE'

CI Report

⚠️ Action Required:

• Please check the failed tests and fix your PR
• If you cannot view the failures, ask the CI triggerer to share details
• Once fixed, request an NVIDIA team member to trigger CI again

CI Agent Failure Analysis

Link to invocation

[nvchenghaoz]

/bot skip --comment "post merge test fix"

[suyoggupta]

is this the only affected model? could we proactively apply this fix to other model yamls?

[nvchenghaoz]

/bot skip --comment "post merge test fix"

[tensorrt-cicd]

PR_Github #46834 [ skip ] triggered by Bot. Commit: 284f792 Link to invocation

[tensorrt-cicd]

PR_Github #46834 [ skip ] completed with state SUCCESS. Commit: 284f792
Skipping testing for commit 284f792

Link to invocation