RamaLama is an open-source developer tool that simplifies the local serving of AI models from any source and facilitates their use for inference in production, all through the familiar language of containers.

Turn any computer or edge device into a command center for your computer vision projects.

The simplest way to serve AI/ML models in production

An open-source computer vision framework to build and deploy apps in minutes

Python + Inference - Model Deployment library in Python. Simplest model inference server ever.

A REST API for Caffe using Docker and Go

⚡Local-first AI inference server with OpenAI API compatibility, auto-discovery, hot model swapping, and tool calling. Single-binary Rust solution for GGUF models with LoRA support. FREE now, FREE forever.

This is a repository for an nocode object detection inference API using the Yolov3 and Yolov4 Darknet framework.

Work with LLMs on a local environment using containers

This is a repository for an nocode object detection inference API using the Yolov4 and Yolov3 Opencv.

This is a repository for an object detection inference API using the Tensorflow framework.

ONNX Runtime Server: The ONNX Runtime Server is a server that provides TCP and HTTP/HTTPS REST APIs for ONNX inference.

Serving AI/ML models in the open standard formats PMML and ONNX with both HTTP (REST API) and gRPC endpoints

Orkhon: ML Inference Framework and Server Runtime

K3ai is a lightweight, fully automated, AI infrastructure-in-a-box solution that allows anyone to experiment quickly with Kubeflow pipelines. K3ai is perfect for anything from Edge to laptops.

Deploy DL/ ML inference pipelines with minimal extra code.

A standalone inference server for trained Rubix ML estimators.

[⛔️ DEPRECATED] Friendli: the fastest serving engine for generative AI

Wingman is the fastest and easiest way to run Llama models on your PC or Mac.

Advanced inference pipeline using NVIDIA Triton Inference Server for CRAFT Text detection (Pytorch), included converter from Pytorch -> ONNX -> TensorRT, Inference pipelines (TensorRT, Triton server - multi-format). Supported model format for Triton inference: TensorRT engine, Torchscript, ONNX