Serve PyTorch Models at Scale with Triton Inference Server
Автор: Ram Vegiraju
Загружено: 2025-04-25
Просмотров: 4090
In this video we start a new series focused around deploying ML models with Triton Inference Server. In this case we specifically focus on using the PyTorch backend to deploy TorchScript based models.
Video Resources
Notebook Link: https://github.com/RamVegiraju/triton...
Triton Container Releases: https://docs.nvidia.com/deeplearning/...
Timestamps
0:00 Introduction
1:10 What is a Model Server
4:50 Why Triton
7:52 Hands-On
#pytorch #nvidia #tritoninference #inference #modelserving
Доступные форматы для скачивания:
Скачать видео mp4
-
Информация по загрузке: