Management Dashboard for Torchserve

Serving PyTorch models with TorchServe 🔥

Deploy DL/ ML inference pipelines with minimal extra code.

Torchserve server using a YoloV5 model running on docker with GPU and static batch inference to perform production ready and real time inference.

Deploy FastAI Trained PyTorch Model in TorchServe and Host in Amazon SageMaker Inference Endpoint

A minimalistic and pluggable machine learning platform for Kubernetes.

TorchServe+Streamlit for easily serving your HuggingFace NER models

Deploy Swin Transformer using TorchServe

Slides and notebook for the workshop on serving bert models in production

Pushing Text To Speech models into production using torchserve, kubernetes and react web app 😄

FastAPI middleware for comparing different ML model serving approaches

Twin Neural Network Training with PyTorch and fast.ai and its Deployment with TorchServe on Amazon SageMaker

How to deploy TorchServe on an Amazon EKS cluster for inference.

Deploy FastAI Trained PyTorch Model in TorchServe and Host in GCP's AI-Platform Prediciton.

This paper compares Flask, FastAPI, and TorchServe for deploying PyTorch models. Flask is simple, FastAPI adds performance, and TorchServe is best for large-scale production. FastAPI is ideal for small deployments, while TorchServe suits complex environments. AWS Lambda is suggested for advanced use cases.

Quick and easy tutorial to serve HuggingFace sentiment analysis model using torchserve

DET is an end-to-end tool for extracting Key-Value pairs from a variety of documents, built entirely on PyTorch and served using TorchServe.

Predicting musical valence of Spotify songs using PyTorch.

This repo implements a minimalistic pytorch_lightning + neptune + torchserve flow for (computer vision) model training and deployment

TorchServe images with specific Python version working out-of-the-box.