[None][fix] Exclude Qwen3 VL vision model from quantization

[2ez4bz]

Summary by CodeRabbit

• Refactor
  • Updated KV cache quantization configuration initialization for the vision encoder in Qwen3VL models.

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.

[2ez4bz]

/bot run

[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: 9219dc00-0524-4077-866e-8519e467d234

📥 Commits

Reviewing files that changed from the base of the PR and between 5f3fd3a and 795a373.

📒 Files selected for processing (1)

• tensorrt_llm/_torch/models/modeling_qwen3vl.py

---

📝 Walkthrough

Walkthrough

The PR modifies Qwen3VLModelBase initialization to reset the quantization configuration to a plain QuantConfig() instead of preserving the previous KV cache quantization algorithm. The accompanying comment is updated to reflect the exclusion of KV cache quantization for the vision encoder.

Changes

Quantization Config Initialization

Layer / File(s)	Summary
Model Init Quantization Config Reset tensorrt_llm/_torch/models/modeling_qwen3vl.py	Qwen3VLModelBase vision wrapper initialization resets self.model_config.quant_config to QuantConfig(), dropping the previous kv_cache_quant_algo passthrough. The comment is updated to document that KV cache quantization is excluded for the vision encoder.

Estimated code review effort

🎯 2 (Simple) | ⏱️ ~8 minutes

🚥 Pre-merge checks | ✅ 3 | ❌ 2

❌ Failed checks (2 warnings)

Check name	Status	Explanation	Resolution
Description check	⚠️ Warning	The PR description is incomplete; it contains only the template with no actual content in Description, Test Coverage, or specific PR details sections.	Fill in the Description section explaining the issue and rationale, add Test Coverage section listing relevant tests, and provide specific details in the PR Checklist.
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 and specifically describes the main change: excluding Qwen3 VL vision model from quantization, which aligns with the code change of re-initializing quantization config.
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.}

[tensorrt-cicd]

PR_Github #47782 [ run ] triggered by Bot. Commit: 795a373 Link to invocation

[tensorrt-cicd]

PR_Github #47782 [ run ] completed with state SUCCESS. Commit: 795a373
/LLM/main/L0_MergeRequest_PR pipeline #37674 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

[2ez4bz]

/bot run

[tensorrt-cicd]

PR_Github #47914 [ run ] triggered by Bot. Commit: 795a373 Link to invocation

[tensorrt-cicd]

PR_Github #47914 [ run ] completed with state SUCCESS. Commit: 795a373
/LLM/main/L0_MergeRequest_PR pipeline #37761 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

[yechank-nvidia]

/bot run

[tensorrt-cicd]

PR_Github #47932 [ run ] triggered by Bot. Commit: 795a373 Link to invocation

[tensorrt-cicd]

PR_Github #47932 [ run ] completed with state SUCCESS. Commit: 795a373
/LLM/main/L0_MergeRequest_PR pipeline #37778 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

[2ez4bz]

/bot run

[tensorrt-cicd]

PR_Github #49759 [ run ] triggered by Bot. Commit: 96f1e7a Link to invocation

[tensorrt-cicd]

PR_Github #49759 [ run ] completed with state SUCCESS. Commit: 96f1e7a
/LLM/main/L0_MergeRequest_PR pipeline #39359 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

[2ez4bz]

/bot run

[tensorrt-cicd]

PR_Github #49777 [ run ] triggered by Bot. Commit: 96f1e7a Link to invocation

[tensorrt-cicd]

PR_Github #49777 [ run ] completed with state SUCCESS. Commit: 96f1e7a
/LLM/main/L0_MergeRequest_PR pipeline #39374 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

[2ez4bz]

/bot run

[tensorrt-cicd]

PR_Github #50399 [ run ] triggered by Bot. Commit: ec466d1 Link to invocation

[tensorrt-cicd]

PR_Github #50399 [ run ] completed with state SUCCESS. Commit: ec466d1
/LLM/main/L0_MergeRequest_PR pipeline #39923 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

[2ez4bz]

/bot run

[tensorrt-cicd]

PR_Github #50452 [ run ] triggered by Bot. Commit: ec466d1 Link to invocation

[tensorrt-cicd]

PR_Github #50452 [ run ] completed with state SUCCESS. Commit: ec466d1
/LLM/main/L0_MergeRequest_PR pipeline #39971 completed with status: 'SUCCESS'
Pipeline passed with automatic retried tests. Check the rerun report for details.

CI Report

Link to invocation