There are 2 repositories under serving-pytorch-models topic.
In this repository, I will share some useful notes and references about deploying deep learning-based models in production.
ClearML - Model-Serving Orchestration and Repository Solution
A collection of model deployment library and technique.
Segmenting people on photos using IOS devices [Pytorch; Unet]
Universal Semantic Annotator (LREC 2022)
Chatting-Day's Dialogue State Tracking (DST)
Simple HTTP serving for PyTorch 🚀
TorchServe images with specific Python version working out-of-the-box.
A message queue based server architecture to asynchronously handle resource-intensive tasks (e.g., ML inference)
End-to-end NBA analytics pipeline for predicting game outcomes and attendance using PyTorch, MLflow, and ONNX. Includes data scraping, model training, quantization, and scalable deployment with FastAPI and Triton Inference Server.
Serving PyTorch model using flask and docker
A proof-of-concept on how to install and use Torchserve in various mode