Deploy Complex ML Workflows with Triton Inference Server Ensembles

In this video we explore how we can stitch together multiple models into complex workflows and deploy as a singular unit using Triton Ensembles. ALSO apologies I realize some noise was picked up on from the iPad, messed up my mic settings a little for this video by accident will be fixed for the next video, sorry for the trouble! Please leave any questions or doubts down below or reach out directly as always. Video Resources - Sample Code: https://github.com/RamVegiraju/triton-inference-server-examples/tree/master/ensemble - Ensemble Documentation: https://docs.nvidia.com/deeplearning/triton-inference-server/user-guide/docs/user_guide/ensemble_models.html Timestamps 0:00 Introduction 0:55 ML Workflows 2:33 Ensembles 5:00 Hands-On #sagemaker #nvidia #tritoninferenceserver #modelserving #machinelearning #transformers #huggingface