KTransformers v0.7.1: Qwen VLM and Kimi LoRA Fine-Tuning

KTransformers v0.7.1 brings together Qwen VLM and Kimi K2.5 / K2.6 LoRA fine-tuning through LLaMA-Factory. CPU–GPU heterogeneous execution combines host memory with GPU acceleration for multimodal adaptation and personalized dialogue.

🚀 Core Highlights

• Qwen VLM MoE fine-tuning: BF16 image–text LoRA for Qwen3-VL-30B-A3B-Instruct and Qwen3.5-35B-A3B, covering vision, language, and routed-expert modules. Contributed by Bowen Wu (@Illumination111) in #2156.
• Native RAWINT4 Kimi fine-tuning: text LoRA for Kimi K2.5 / K2.6 using the original packed expert weights, avoiding full-model BF16 expansion.

📦 Installation

Follow the model-specific guides for the complete dependency setup, data preparation, and training commands:

• Qwen VLM LoRA Fine-Tuning Guide
• Kimi LoRA Training and Inference Guide

🌟 Contributors

Thanks to @JimmyPeilinLi, @Illumination111, @yyj6666667, and everyone who contributed code, documentation, and testing.

Special thanks to @05yuki for valuable insights into MXFP4 kernels and performance optimization.