PyTorch is a Python package that provides two high-level features: - Tensor computation (like NumPy) with strong GPU acceleration - Deep neural networks built on a tape-based autograd system You can reuse your favorite Python packages such as NumPy, SciPy, and Cython to extend PyTorch when needed.
| Uploaded | Mon Mar 31 23:45:45 2025 |
| md5 checksum | 405e101c047829e349060d4848f9cebd |
| arch | x86_64 |
| build | gpu_cuda118py311h6b76543_100 |
| build_number | 100 |
| depends | __cuda >=11.8, _openmp_mutex, blas * openblas, cudatoolkit >=11.8.0,<11.9.0a0, cudnn >=8.9,<9.0a0, cudnn >=8.9.2.26,<9.0a0, cupti >=11.8.0,<12.0a0, filelock, fsspec, jinja2, libgcc-ng >=11.2.0, libopenblas >=0.3.21,<1.0a0, libprotobuf >=3.20.3,<3.21.0a0, libstdcxx-ng >=11.2.0, magma >=2.7.1,<3.0a0, networkx, numpy >=1.23.5,<2.0a0, python >=3.11,<3.12.0a0, sympy, torchtriton 2.3.*, typing_extensions >=4.8.0 |
| license | BSD-3-Clause |
| license_family | BSD |
| md5 | 405e101c047829e349060d4848f9cebd |
| name | pytorch |
| platform | linux |
| sha1 | d855c81f45800a7418ec8b31e4bc31ed685d3bc7 |
| sha256 | 2868675efa04417ba466db7152fc54deb5d08ea60192c5e59fb93d4fc2a490c9 |
| size | 589167008 |
| subdir | linux-64 |
| timestamp | 1719553619891 |
| version | 2.3.0 |