PyTorch 2. x Learn about PyTorch 2 x: faster performance, dynamic shapes, distributed training, and torch compile
PyTorch – PyTorch PyTorch is an open source machine learning framework that accelerates the path from research prototyping to production deployment Built to offer maximum flexibility and speed, PyTorch supports dynamic computation graphs, enabling researchers and developers to iterate quickly and intuitively Its Pythonic design and deep integration with native Python tools make it an accessible and powerful
YOLOv5 – PyTorch Load From PyTorch Hub This example loads a pretrained YOLOv5s model and passes an image for inference YOLOv5 accepts URL, Filename, PIL, OpenCV, Numpy and PyTorch inputs, and returns detections in torch, pandas, and JSON output formats See the YOLOv5 PyTorch Hub Tutorial for details
PyTorch at NVIDIA GTC 2026: Join Us in San Jose! – PyTorch We’re excited to announce that PyTorch will have a strong presence at NVIDIA GTC 2026, from March 16-19, 2026 in San Jose! Whether you’re a seasoned PyTorch developer or just getting started, we invite you to join us for demos, talks, hands-on labs, and opportunities to connect with PyTorch core maintainers and community experts
Blog – PyTorch Why Is PyTorch Compile So Fast: Kernel Fusion When you use PyTorch's compiler, your model runs faster, up to 10x faster But what's… May 27, 2026 Blog
PyTorch 2. 2: FlashAttention-v2 integration, AOTInductor PyTorch 2 2 introduces a new ahead-of-time extension of TorchInductor called AOTInductor, designed to compile and deploy PyTorch programs for non-python server-side torch distributed supports a new abstraction for initializing and representing ProcessGroups called device_mesh