Show HN: Trellis2.c – Local 3D generation with Vulkan and CUDA

A developer released Trellis2.c, a native executable for local 3D generation that supports both CUDA and Vulkan backends, aiming to eliminate Python/PyTorch dependencies. The project, tested primarily on an NVIDIA RTX 4090, seeks community feedback on AMD and Intel GPU performance. Performance remains a limitation, with inference slower than optimized PyTorch or Vulkan implementations.

Hi HN, I started this because I wanted something in the spirit of llama.cpp and stable-diffusion.cpp, but for local 3D generation model: native executables, no Python/PyTorch runtime, and both CUDA and Vulkan backends. I’ve mainly tested it on an NVIDIA RTX 4090. I’m particularly interested in Vulkan results on AMD and Intel GPUs, where driver behavior and memory allocation may differ. If you try it, GPU, driver, OS details, and failure logs would be extremely helpful. The main limitation right now is performance. The implementation has not yet been heavily optimized, so inference is currently slower than mature, fully optimized PyTorch or Vulkan backends. There is still substantial room for kernel, memory-use, and scheduling improvements. Comments URL: https://news.ycombinator.com/item?id=48931429 https://news.ycombinator.com/item?id=48931429 Points: 1 Comments: 0