Model Serving
Showing 36 of 40 projects
A platform to run, manage, and serve open-source large language models (LLMs) locally or on your own infrastructure.
A high-throughput, memory-efficient inference and serving engine for large language models (LLMs).
An open platform for training, serving, and evaluating large language model based chatbots.
A minimalist, high-performance machine learning framework for Rust with a focus on serverless inference and GPU support.
A composable, modular, and scalable machine learning toolkit for building AI platforms on Kubernetes.
A low-code declarative framework for building custom LLMs, neural networks, and other AI models with YAML configurations.
An open-source inference serving platform for deploying AI models from multiple frameworks across cloud, data center, and edge devices.
A practical booklet covering the four main steps of designing machine learning systems with 27 interview questions.
A Python library for building production-ready model inference APIs, job queues, and multi-model serving systems for AI applications.
A platform for deploying, managing, and scaling machine learning models in production on AWS infrastructure.
A fast, flexible, and hardware-aware LLM inference engine with zero-config support for any Hugging Face model.
An open-source MLOps/LLMOps suite for experiment management, data management, pipelines, orchestration, scheduling, and model serving.
A curated collection of resources for building, training, serving, and optimizing production-grade Large Language Model applications.
An MLOps framework to package, deploy, monitor, and manage thousands of production machine learning models on Kubernetes.
An open-source deep learning API and server written in C++ that supports multiple backends like PyTorch, TensorRT, and TensorFlow for training and inference.
A JAX/Flax-based framework for easy and scalable pre-training, fine-tuning, evaluation, and serving of large language models.
A Go library that simplifies TensorFlow's Go bindings with method chaining, automatic scoping, and type conversion.
A command-line tool for creating reproducible, container-based development environments for AI/ML workflows.
A visual workflow-based AI deployment framework for multi-platform and multi-backend inference, supporting large models and edge devices.
An open-source machine learning system for the end-to-end data science lifecycle from data preparation to model serving.
A tool to package, serve, and deploy any ML model on any platform using a GitOps approach.
A Ruby library for building and serving predictive models with support for PMML and integration with Python and R models.
A production-ready FastAPI skeleton app for serving machine learning models with built-in authentication and testing.
A book teaching practical patterns for building scalable and reliable distributed machine learning systems using Kubernetes, TensorFlow, Kubeflow, and Argo Workflows.
A JAX-based framework for streamlined training, fine-tuning, and high-performance serving of large language and multimodal models.
A TensorFlow-based object detection model that localizes and identifies multiple objects in images using SSD MobileNet V1 or Faster R-CNN ResNet101.
A TensorFlow-based model that generates descriptive captions for images using an Inception-v3 encoder and LSTM decoder.
A Docker-based speech recognition model that converts short English WAV audio files into text using Mozilla's DeepSpeech.
A TensorFlow/Keras LSTM model for hourly weather forecasting, offering univariate, multivariate, and multistep prediction modes.
Detects humans in images and estimates their poses by identifying body parts and connecting them with pose lines.
Generates embedding vectors from audio files using a TensorFlow model trained on AudioSet, deployable as a Docker container.
A pre-trained BERT-based model for detecting positive or negative sentiment in short text fragments.
Deploy a neural network model that transfers artistic styles from one image to another using a ResNet-based architecture.
A pre-trained image classifier that recognizes 365 different scene and location types using a ResNet18 model fine-tuned on Places365.
A TensorFlow-based image segmentation model that assigns each pixel in an image to one of 21 object classes from the PASCAL VOC dataset.
A pre-trained deep learning model for image classification that identifies 1000 object classes using the Inception-ResNet-v2 architecture.
Related Tags
Found a gem we're missing?
Open-Awesome is built by the community, for the community. Submit a project, suggest an awesome list, or help improve the catalog on GitHub.