← Wednesday, October 21, 2026InferenceRelease

PyTorch 2.15 adds FP8 and faster decoding paths to MPS

huggingface.co 10 min read Editor score 7/10

The MPS update adds FP8, faster language-model decoding paths through linear layers and softmax, and dedicated Metal kernels for audio, video and training. These backend changes matter to engineers running models on Apple hardware.

What

PyTorch 2.15 adds FP8 support and Metal-kernel paths to the MPS backend for Mac model workloads.

How

Updates include specialized linear and softmax decoding, grouped matmul for MoE, and reduced Wan2.2 VAE decode memory.

Why it matters

These backend improvements expand local model capacity and speed, making Mac GPUs more useful for inference and multimedia workloads.

Read on huggingface.co →

Headline, summary, brief and diagram are written by a model from the source's own text; the link, byline and numbers come from the source. Read the original before relying on a claim.