Deployment of TensorFlow models into production with TensorFlow Serving, Docker, Kubernetes and Microsoft Azure

Serving ML model with fastapi

Tutorial on serving LLMs via vllm in docker containers on kubernetes clusters

Basic example of Tensorflow Serving

Template for a simple API to have a model serving in production.

A proof-of-concept on how to install and use Torchserve in various mode

Decopled serving stack using FastAPI, Kafka, and MongoDB - Example

A Simple way to deploy your tensorflow.keras model using Flask

AsyncIO serving for data science models

Simple TensorFlow Estimator 1.x example with Serving API.

End to End Text Classifaction MLOps Project using Tekton Pipelines

An object oriented (OOP) approach to train Tensorflow models and serve them using Tensorflow Serving.

Docker-based Machine Learning models serving

Recipes for reproducing training and serving benchmarks for large machine learning models using GPUs on Google Cloud.

ML

📦 Automated dataset management for ML using Docker containers on AWS

Python wrapper class for OpenVINO Model Server. User can submit inference request to OVMS with just a few lines of code.

EdgeServe is a decentralized model serving system that optimizes data movements and model placements within an edge cluster.

A simple, consolidated, extensible gRPC-based client implementation for querying TensorFlow Model Server.