A C++ inference server that serves OpenVINO-optimized generative AI and classic deep learning models over OpenAI-compatible and KServe APIs.
952284C++Apache-2.0Updated 5 hours ago
#openvino
Curated GitHub repositories related to openvino, with AI summaries and key stats.
A C++ inference server that serves OpenVINO-optimized generative AI and classic deep learning models over OpenAI-compatible and KServe APIs.
A Python framework for compressing neural networks via quantization, pruning and sparsity to speed up inference in OpenVINO, PyTorch and ONNX.