Migrate Qwen3-ASR and Qwen3-Omni to HybridModel

[Phlip79]

Summary

• migrate Qwen3-ASR language-model integration to the shared Qwen Hybrid runtime
• migrate Qwen3-Omni thinker-side language and MoE integration to HybridModel
• update conversion mappings and multimodal model/provider wiring
• update focused ASR and Omni unit coverage

Models modified

Qwen3-ASR checkpoints using Qwen3ASRForConditionalGeneration:

• Qwen/Qwen3-ASR-1.7B

Qwen3-Omni checkpoints using Qwen3OmniMoeForConditionalGeneration:

• Qwen/Qwen3-Omni-30B-A3B-Instruct

Stack

This is PR 4 of 4. Merge the stack in order:

1. Migrate Qwen3 dense and MoE models to HybridModel #4747 - Qwen3 dense and MoE
2. Migrate Qwen3-Next and Qwen3.5 models to HybridModel #4836 - Qwen3-Next and Qwen3.5 text
3. Migrate Qwen VL models to HybridModel #4837 - Qwen3-VL and Qwen3.5-VL
4. Migrate Qwen3-ASR and Qwen3-Omni to HybridModel #4838 - Qwen3-ASR and Qwen3-Omni

Validation

• uv run --no-project --with pre-commit pre-commit run --all-files
• This stack tip is tree-identical to the original Migrate Qwen3 dense and MoE models to HybridModel #4747 implementation.

[copy-pr-bot]

This pull request requires additional validation before any workflows can run on NVIDIA's runners.

Pull request vetters can view their responsibilities here.

Contributors can view more details about this message here.