Overview
ONNX Runtime is a cross-platform inference and training machine-learning accelerator.
ONNX Runtime is an accelerator for machine learning models with multi-platform support and a flexible interface to integrate with hardware-specific libraries. ONNX Runtime can be used with models from PyTorch, Tensorflow/Keras, TFLite, scikit-learn, and other frameworks.
This release of RocketCE is based on Release OpenCE v1.3.1 and it includes ONNX Runtime v1.7.2.
These packages are supported for both Power 9 and Power 10 Systems of IBM with linux-ppc64le.
CPU Support
RocketCE includes CPU only variant of ONNX Runtime which is built without GPU support.
GPU Support
This version of Tensorflow will not support GPU variant. Support of GPU variant will be provided in coming releases. For more information, refer main page of OpenCE
Installation instructions
CPU Variant
To install CPU only variant of ONNX Runtime, run the following command:
- conda install -c rocketce onnxruntime
Once the installation is success, validate the installation by running the following command which lists the package onnxruntime which was pulled from rocketce channel
------------------------------
Rajesh Nukala
Rocket Internal - All Brands
------------------------------