[https://nvbugs/5938603][fix] Cherry-pick Fix E/PD disagg chunked prefill bug (#11805)

[pcastonguay]

Summary by CodeRabbit

• Bug Fixes

  • Improved multimodal data validation in Qwen models by enforcing stricter presence checks for multimodal embeddings, preventing false positives when data is present but invalid.

• Tests

  • Added smoke test for chunked prefill with multimodal Qwen models to verify engine stability and prevent crashes.

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.

[pcastonguay]

/bot run --disable-fail-fast

[coderabbitai]

No actionable comments were generated in the recent review. 🎉

ℹ️ Recent review info

Configuration used: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Pro

📥 Commits

Reviewing files that changed from the base of the PR and between e922a86 and 2a340bf.

📒 Files selected for processing (3)

• tensorrt_llm/_torch/models/modeling_qwen2vl.py
• tensorrt_llm/_torch/models/modeling_qwen3vl.py
• tests/unittest/_torch/multimodal/test_mm_encoder_standalone.py

---

📝 Walkthrough

Walkthrough

Changes tighten multimodal embedding condition checks in two Qwen VL model files from truthiness tests to explicit None checks, and add a new smoke test for chunked prefill functionality with the Qwen VL model.

Changes

Cohort / File(s)	Summary
Multimodal Embedding Condition Fixes tensorrt_llm/_torch/models/modeling_qwen2vl.py, tensorrt_llm/_torch/models/modeling_qwen3vl.py	Changed multimodal embedding condition from truthiness check to explicit None check, preventing false positives when multimodal_embedding is falsy but present.
Chunked Prefill Test tests/unittest/_torch/multimodal/test_mm_encoder_standalone.py	Added new smoke test function test_chunked_prefill_multimodal_smoke that verifies chunked prefill functionality with Qwen VL models does not crash and produces non-empty outputs.

Estimated code review effort

🎯 2 (Simple) | ⏱️ ~12 minutes

🚥 Pre-merge checks | ✅ 1 | ❌ 2

❌ Failed checks (2 warnings)

Check name	Status	Explanation	Resolution
Description check	⚠️ Warning	The PR description contains only the template structure with no substantive content filled in; the Description and Test Coverage sections are empty.	Complete the Description section explaining the issue and solution, and the Test Coverage section listing relevant tests that safeguard these changes.
Docstring Coverage	⚠️ Warning	Docstring coverage is 50.00% which is insufficient. The required threshold is 80.00%.	Write docstrings for the functions missing them to satisfy the coverage threshold.

✅ Passed checks (1 passed)

Check name	Status	Explanation
Title check	✅ Passed	The title clearly identifies the fix for a specific E/PD disagg chunked prefill bug (NVBugs 5938603) and references a related PR.

_{✏️ Tip: You can configure your own custom pre-merge checks in the settings.}

✨ Finishing Touches

🧪 Generate unit tests (beta)

• Create PR with unit tests
• Post copyable unit tests in a comment

---

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

[tensorrt-cicd]

PR_Github #37415 [ run ] triggered by Bot. Commit: 2a340bf Link to invocation

[tensorrt-cicd]

PR_Github #37415 [ run ] completed with state SUCCESS. Commit: 2a340bf
/LLM/release-1.3.0rc5.post1/L0_MergeRequest_PR pipeline #13 completed with status: 'FAILURE'

⚠️ 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

[pcastonguay]

/bot run --disable-fail-fast

[tensorrt-cicd]

PR_Github #37507 [ run ] triggered by Bot. Commit: 2a340bf Link to invocation

[tensorrt-cicd]

PR_Github #37507 [ run ] completed with state SUCCESS. Commit: 2a340bf
/LLM/release-1.3.0rc5.post1/L0_MergeRequest_PR pipeline #16 completed with status: 'SUCCESS'

Link to invocation

[brb-nv]

LGTM.