The Holoscan container includes the Holoscan libraries, GXF extensions, headers, example source code, and sample datasets. It is the recommended way to run the Holoscan examples or build your own applications.
Triton Inference Server is an open source software that lets teams deploy trained AI models from any framework, from local or cloud storage and on any GPU- or CPU-based infrastructure in the cloud, data center, or embedded devices.
PyTorch is a GPU accelerated tensor computational framework. Functionality can be extended with common Python libraries such as NumPy and SciPy. Automatic differentiation is done with a tape-based system at the functional and neural network layer levels.
NVIDIA TensorRT is a C++ library that facilitates high-performance inference on NVIDIA graphics processing units (GPUs). TensorRT takes a trained network and produces a highly optimized runtime engine that performs inference for that network.
NVIDIA Optimized Deep Learning Framework, powered by Apache MXNet is a deep learning framework that allows you to mix the flavors of symbolic programming and imperative programming to maximize efficiency and productivity.
PaddlePaddle is the first independent R&D deep learning platform in China. It has been widely adopted by manufacturing, agriculture, enterprise service, serving 4 million + developers, 157,000 companies and generating 476,000 models.
The Merlin PyTorch container allows users to do preprocessing and feature engineering with NVTabular, and then train a deep-learning based recommender system model with PyTorch, and serve the trained model on Triton Inference Server.