[None][feat] Add BaseMultimodalDummyInputsBuilder to minimaxm3_vl

[pcicotti]

Background

MiniMaxM3VLInputProcessor was missing BaseMultimodalDummyInputsBuilder as a base class, causing the following error at runtime:

AttributeError: 'MiniMaxM3VLInputProcessor' object has no attribute 'get_preferred_media_io_kwargs'

Summary

Add BaseMultimodalDummyInputsBuilder to the dynamically constructed _Registered class in get_minimax_m3_vl_input_processor_cls(), alongside the existing BaseMultimodalInputProcessor base.

Impact

No functional change beyond fixing the missing attribute — no new configuration, no API surface change.

Dev Engineer Review

• Updated the dynamically registered MiniMax M3 VL input processor to inherit from BaseMultimodalDummyInputsBuilder alongside BaseMultimodalInputProcessor.
• This resolves the missing get_preferred_media_io_kwargs interface required by the multimodal pipeline.
• Change is narrowly scoped, introduces no configuration or public API changes, and has no apparent performance or error-handling impact.

QA Engineer Review

No test changes.

[pcicotti]

/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: 33cf4940-f3a5-45bf-8651-da90df2bf6a4

📥 Commits

Reviewing files that changed from the base of the PR and between 6fabfdc and b1a0487.

📒 Files selected for processing (1)

• tensorrt_llm/_torch/models/modeling_minimaxm3_vl.py

---

Walkthrough

The dynamically registered MiniMaxM3VLInputProcessor class now inherits BaseMultimodalDummyInputsBuilder in addition to its existing multimodal input processor bases.

Changes

MiniMaxM3 VL processor registration

Layer / File(s)	Summary
Extend registered processor interface tensorrt_llm/_torch/models/modeling_minimaxm3_vl.py	The dynamically created _Registered class imports and inherits BaseMultimodalDummyInputsBuilder.

Estimated code review effort: 1 (Trivial) | ~5 minutes

Suggested reviewers: brb-nv

🚥 Pre-merge checks | ✅ 5

✅ Passed checks (5 passed)

Check name	Status	Explanation
Title check	✅ Passed	The title is concise, follows the repository's format, and clearly describes the main change.
Description check	✅ Passed	The description explains the background, fix, and impact, but omits the requested Test Coverage section.
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.

✨ Finishing Touches

🧪 Generate unit tests (beta)

• Create PR with unit tests

---

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

[tensorrt-cicd]

PR_Github #60832 [ run ] triggered by Bot. Commit: b1a0487 Link to invocation

[tensorrt-cicd]

PR_Github #60832 [ run ] completed with state SUCCESS. Commit: b1a0487
/LLM/main/L0_MergeRequest_PR pipeline #49108 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

[pcicotti]

/bot run --disable-fail-fast

[tensorrt-cicd]

PR_Github #61009 [ run ] triggered by Bot. Commit: b1a0487 Link to invocation

[tensorrt-cicd]

PR_Github #61009 [ run ] completed with state SUCCESS. Commit: b1a0487
/LLM/main/L0_MergeRequest_PR pipeline #49267 completed with status: 'SUCCESS'

CI Report

Link to invocation