These are the examples for the webinar on Triton Inference Server. For any additional information, feel free to contact Dmitry Mironov dmitrym@nvidia.com
This repository contains three demos:
- Model Analyzer demo in English and in Russian
- Basic TensorRT + Triton demo (English)
- [Work In Progress] Triton in Kubernetes demo English only
Additional file is onnx-to-triton.ipynb, it can be used to generated a basic Triton config.pbtxt file from an ONNX file.
SPDX-FileCopyrightText: Copyright (c) 2021 NVIDIA CORPORATION & AFFILIATES. All rights reserved. SPDX-License-Identifier: MIT Please, see the LICENSE file.