ONNX Runtime is a cross-platform machine-learning model accelerator, with a flexible interface to integrate hardware-specific libraries. ONNX Runtime can be used with models from PyTorch, Tensorflow/Keras, TFLite, scikit-learn, and other frameworks.
| Uploaded | Mon Mar 31 22:59:10 2025 |
| md5 checksum | ae2a32e9e0dd2fdd4cbbca3d26e5eaef |
| arch | x86_64 |
| build | gpu_cuda124py312h05d824c_0 |
| depends | __cuda, coloredlogs, cuda-cudart >=12.4.127,<13.0a0, cuda-cupti >=12.4.127,<13.0a0, cuda-nvrtc >=12.4.127,<13.0a0, cuda-version >=12.4,<13, cudnn >=9.1,<10.0a0, libcublas >=12.4.5.8,<13.0a0, libcufft >=11.2.1.3,<12.0a0, libcurand >=10.3.5.147,<11.0a0, libcusparse >=12.3.1.170,<13.0a0, libgcc-ng >=11.2.0, libstdcxx-ng >=11.2.0, numpy >=1.19,<3, numpy >=1.21.6,<3, packaging, protobuf, python >=3.12,<3.13.0a0, python-flatbuffers, sympy |
| license | MIT AND BSL-1.0 |
| license_family | MIT |
| md5 | ae2a32e9e0dd2fdd4cbbca3d26e5eaef |
| name | onnxruntime |
| platform | linux |
| sha1 | d5a4ebea75b2d65d2208372dabf4d0d8834bb5b9 |
| sha256 | b668a9d667691ce10383137380dc26e0dacaf6fcaaf93dc91c34126876e08015 |
| size | 115369694 |
| subdir | linux-64 |
| timestamp | 1738187620858 |
| version | 1.20.1 |