Skip to content

[https://nvbugs/6248744][fix] Added trust_remote_code=True to the LLM(...) constructor and removed the… - #14892

Merged
yibinl-nvidia merged 2 commits into
NVIDIA:mainfrom
tensorrt-cicd:repair-bot-bug6248744
Jun 5, 2026
Merged

[https://nvbugs/6248744][fix] Added trust_remote_code=True to the LLM(...) constructor and removed the…#14892
yibinl-nvidia merged 2 commits into
NVIDIA:mainfrom
tensorrt-cicd:repair-bot-bug6248744

Conversation

@tensorrt-cicd

@tensorrt-cicd tensorrt-cicd commented Jun 3, 2026

Copy link
Copy Markdown
Collaborator

Summary

  • Root cause: PR [https://nvbugs/5996024][fix] Enforce trust_remote_code flag #13527 made the loader honor llm_args.trust_remote_code (default False), but TestNemotron_Nano_12B_V2_VL omits trust_remote_code=True, and the model ships custom HF code requiring it.
  • Fix: Added trust_remote_code=True to the LLM(...) constructor and removed the obsolete waiver; verify run passed (1 passed, MMMU 26.56 vs ref 26.67).
  • Automated fix generated by repair-bot

Test plan

  • Verify fix on the same GPU type as the original failure
  • Check for regressions in related tests

Links

Summary by CodeRabbit

  • Tests
    • Re-enabled a previously skipped test case for multimodal LLM model compatibility, ensuring proper handling of remote code execution scenarios.

@coderabbitai

coderabbitai Bot commented Jun 3, 2026

Copy link
Copy Markdown
Contributor

Review Change Stack

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: b643ccb4-a450-4086-a31a-3a8f714e6472

📥 Commits

Reviewing files that changed from the base of the PR and between d0cfcde and a82a0ee.

📒 Files selected for processing (2)
  • tests/integration/defs/accuracy/test_llm_api_pytorch_multimodal.py
  • tests/integration/test_lists/waives.txt
💤 Files with no reviewable changes (1)
  • tests/integration/test_lists/waives.txt

📝 Walkthrough

Walkthrough

This PR enables a previously-waived multimodal LLM test by adding the trust_remote_code=True parameter to the test's LLM constructor and removing the corresponding waive entry, allowing the test to run instead of being skipped.

Changes

Test Recovery for Nemotron Nano 12B V2 VL

Layer / File(s) Summary
Enable test with remote code trust parameter and waive removal
tests/integration/defs/accuracy/test_llm_api_pytorch_multimodal.py, tests/integration/test_lists/waives.txt
TestNemotron_Nano_12B_V2_VL.test_auto_dtype now passes trust_remote_code=True to the LLM constructor, and the waive entry for test_auto_dtype[forced_chunked_prefill] is removed so the test executes.

Estimated code review effort

🎯 1 (Trivial) | ⏱️ ~3 minutes

Possibly related PRs

  • NVIDIA/TensorRT-LLM#14545: Also modifies tests/integration/test_lists/waives.txt by removing waived test entries.
  • NVIDIA/TensorRT-LLM#14854: Also modifies tests/integration/test_lists/waives.txt to update the set of skipped/waived integration test entries.
🚥 Pre-merge checks | ✅ 4 | ❌ 1

❌ Failed checks (1 warning)

Check name Status Explanation Resolution
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 (4 passed)
Check name Status Explanation
Title check ✅ Passed The title correctly identifies the main change: adding trust_remote_code=True and removing a waiver. It references the bug ticket and uses appropriate [fix] type designation.
Description check ✅ Passed The PR description clearly explains the root cause (PR #13527 behavior change), the fix applied, verification results, and includes test coverage confirmation. However, it is missing the standard template structure with explicit Description and Test Coverage sections.
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.

@longlee0622
longlee0622 force-pushed the repair-bot-bug6248744 branch from a82a0ee to 8f3594e Compare June 3, 2026 10:18
@longlee0622

Copy link
Copy Markdown
Collaborator

/bot run

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator Author

PR_Github #51824 [ run ] triggered by Bot. Commit: 8f3594e Link to invocation

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator Author

PR_Github #51824 [ run ] completed with state SUCCESS. Commit: 8f3594e
/LLM/main/L0_MergeRequest_PR pipeline #41187 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

@yibinl-nvidia

Copy link
Copy Markdown
Collaborator

/bot run

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator Author

PR_Github #51921 [ run ] triggered by Bot. Commit: 8f3594e Link to invocation

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator Author

PR_Github #51921 [ run ] completed with state FAILURE. Commit: 8f3594e
/LLM/main/L0_MergeRequest_PR pipeline #41275 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

@yibinl-nvidia

Copy link
Copy Markdown
Collaborator

/bot run

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator Author

PR_Github #52097 [ run ] triggered by Bot. Commit: 8f3594e Link to invocation

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator Author

PR_Github #52097 [ run ] completed with state SUCCESS. Commit: 8f3594e
/LLM/main/L0_MergeRequest_PR pipeline #41427 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

@yibinl-nvidia

Copy link
Copy Markdown
Collaborator

/bot run

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator Author

PR_Github #52108 [ run ] triggered by Bot. Commit: 8f3594e Link to invocation

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator Author

PR_Github #52108 [ run ] completed with state SUCCESS. Commit: 8f3594e
/LLM/main/L0_MergeRequest_PR pipeline #41438 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

…V2 VL test

Signed-off-by: tensorrt-cicd <90828364+tensorrt-cicd@users.noreply.github.com>
Signed-off-by: tensorrt-cicd <90828364+tensorrt-cicd@users.noreply.github.com>
@tensorrt-cicd
tensorrt-cicd force-pushed the repair-bot-bug6248744 branch from 8f3594e to b8869f2 Compare June 5, 2026 14:52
@yibinl-nvidia

Copy link
Copy Markdown
Collaborator

/bot run

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator Author

PR_Github #52364 [ run ] triggered by Bot. Commit: b8869f2 Link to invocation

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator Author

PR_Github #52364 [ run ] completed with state SUCCESS. Commit: b8869f2
/LLM/main/L0_MergeRequest_PR pipeline #41661 completed with status: 'SUCCESS'

CI Report

Link to invocation

@yibinl-nvidia
yibinl-nvidia merged commit 501b5c2 into NVIDIA:main Jun 5, 2026
7 checks passed
fbxai pushed a commit to fbxai/TensorRT-LLM that referenced this pull request Jun 5, 2026
…LLM(...)` constructor and removed the… (NVIDIA#14892)

Signed-off-by: tensorrt-cicd <90828364+tensorrt-cicd@users.noreply.github.com>
Signed-off-by: NVFB <186336021+NVFB@users.noreply.github.com>
2ez4bz pushed a commit to 2ez4bz/TensorRT-LLM that referenced this pull request Jun 8, 2026
…LLM(...)` constructor and removed the… (NVIDIA#14892)

Signed-off-by: tensorrt-cicd <90828364+tensorrt-cicd@users.noreply.github.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

5 participants