Safetensors is Joining the PyTorch Foundation

This post announces that Safetensors is joining the PyTorch Foundation, moving from a Hugging Face project to a foundation-hosted project under the Linux Foundation. This transition aims to ensure vendor-neutral governance and community ownership. Future developments planned include device-aware loading/saving (direct to CUDA, ROCm), first-class APIs for Tensor Parallel and Pipeline Parallel loading, and formal support for FP8, block-quantized formats (GPTQ, AWQ), and sub-byte integer types.