FICHA · MANJARO

python-pytorch-cuda

Tensors and Dynamic neural networks in Python with strong GPU acceleration (with CUDA)

  • Runtime
  • Dev
  • SCIENCE
  • HARDWARE
  • Dependency only
official+codex · reviewed · May 28, 2026 description in en

Description

Provides the CUDA-enabled PyTorch build for Python tensor and neural-network workloads. It helps PyTorch use supported Nvidia GPUs for training, inference, and accelerated scientific computation.

CUDA workloads require compatible drivers and can reserve large GPU memory. Check hardware support and resource limits before running heavy jobs.

Permissions

Permissions not analysed for this source yet.