#mps

The latest AI and developer news about #mps, with the original source and a short summary.

PyTorch 2.15 improves Mac GPU MoE decoding by 5-6.5x and supports FP8.

·1·2026.10.22 12:00

The update introduces native FP8 support and optimizes Metal kernels, reducing driver memory peaks from 270.135 GiB to 8.108 GiB for video decoding.

·1·2026.10.20 09:00

PyTorch 2.12 significantly strengthens CUDA performance, export, and ROCm support.

·2026.05.14 09:00

Hunyuan3D-Paint and Shape were ported to MLX/MPS for Apple Silicon, making texture generation 3x faster.

·2026.04.24 02:00

Ported Hunyuan3D's image-to-mesh/texture pipeline to Apple Silicon.

·2026.04.23 22:00

TRELLIS.2 was ported to Apple Silicon's MPS, enabling 3D conversion without an NVIDIA GPU.

·1·2026.04.20 16:00

Ported TRELLIS.2 to run 3D generation on Apple Silicon without CUDA.

·1·2026.04.20 09:00