Add Qwen3-VL training adaptation for DFlash

[gq112]

Motivation

This PR adds training adaptation support for Qwen3-VL in the DFlash framework. #461

The goal is to enable end-to-end DFlash draft model training and integration with Qwen3-VL target models under the SpecForge training pipeline.

Modifications

Added Qwen3-VL online DFlash training support.
Added multimodal position id handling for DFlash, including Qwen3-VL mRoPE alignment.
Enabled HF target-side hidden state and position id extraction for VLM inputs.
Updated target embedding / lm head loading for Qwen3-VL weight layouts.
Added qwen3-vl chat template, draft config, and example training script.

Accuracy Test

coming soon

Benchmark & Profiling

Checklist

• Format your code according to the Code Formatting with Pre-Commit.
• Add unit tests as outlined in the Running Unit Tests.
• Update documentation / docstrings / example tutorials as needed, according to Writing Documentation.
• Provide throughput / latency benchmark results and accuracy evaluation results as needed, according to Benchmark and Profiling and Accuracy Results.
• For reviewers: If you haven't made any contributions to this PR and are only assisting with merging the main branch, please remove yourself as a co-author when merging the PR.
• Please feel free to join our Slack channel at https://sgl-fru7574.slack.com/archives/C09784E3EN6 to discuss your PR.

[gemini-code-assist]

Warning

You have reached your daily quota limit. Please wait up to 24 hours and I will start processing your requests again!