Zimeng Xiong's Weblog

Porting Hunyuan3D-2 Texture Generation to MPS

This post documents the process of porting Tencent's Hunyuan3D-2 texture generation pipeline from CUDA to Apple Silicon's Metal Performance Shaders (MPS). The work involved debugging stochastic scheduler behavior, implementing Metal compute kernels for custom rasterization, and integrating with PyTorch's MPS backend.