Pytorch Cuda 12.6 News _hot_ -

PyTorch binaries built with CUDA 12.6 are typically paired with , which introduces:

: As of March 2026, the PyTorch team is transitioning CUDA 13.0 to be the default "stable" variant for PyPI wheels, though 12.6 binaries remain available for specialized downloads. pytorch cuda 12.6 news

Here is some draft content related to PyTorch and CUDA 12.6: PyTorch binaries built with CUDA 12

The news of PyTorch adopting CUDA 12.6 represents a step-change in performance, especially for users of H100/H200 and Blackwell GPUs. However, developers must carefully manage driver upgrades and recompile custom kernels. For most production workloads currently running on A100s with driver 535, sticking with PyTorch 2.4 + CUDA 12.4 is safer. For new projects targeting H100/Blackwell, . For most production workloads currently running on A100s

PyTorch 2.6.0 pre-built wheels for Linux are now compiled natively with CUDA 12.6 and cuDNN 9.2, replacing the previous 12.4-based wheels.