请问当前版本是否支持多模态大模型？

最近Qwen3VL 的MOE结构的模型发布了，请问Ktransformers 是否支持这类VL模型，或者是否有支持的计划？

The issue names Qwen3VL and asks whether KTransformers supports multimodal models or plans to support them, but it names no files, tests, or entry points. Start by checking the current model-support documentation and relevant inference entry points. Done would require a clearly defined support decision or implementation plan, which the issue does not provide.

Written by the indexing model from the issue text.