TRELLIS.2 CUDA kernels on HF Kernels cut BVH build from 7.1s to 5ms

ariG23498 · x · 2026-11-19

Hugging Face's kernels project shipped two standalone CUDA C++ kernels from Microsoft's TRELLIS.2 image-to-3D pipeline (suvadityamuk/trellis2-kernels), moving serial CPU mesh post-processing steps to GPU:

Usage is pip install -U kernels then getkernel("suvadityamuk/trellis2-kernels"); Metal and ROCm kernels are coming next.

Original post →

More from Infra

Infra channel →