Model Serving & Inference

Jina Serve helps developers build multimodal AI applications with cloud-native tools.

Run image model inference with FLUX through the official repository from Black Forest Labs.

PrivateGPT provides an API layer for local model based AI applications, including RAG, tools, MCP, and text to SQL.

Uniform deep learning inference framework for mobile, desktop and server.

NVIDIA Triton Inference Server provides an inference solution for deploying models in cloud and edge environments.

BitNet provides an inference framework for one-bit large language models.

MAI Playground lets users experiment with Microsoft AI models, including image generation, transcription, and voice.

Sonar provides large-scale inference for language models through the project hosted in this repository.

LLMKube runs self hosted LLM inference across heterogeneous GPU fleets using Kubernetes and several model runtimes.

ANEE wraps pretrained transformer inference with an energy budget and early exits inside model execution.

PowerInfer supports serving large language models for local deployment and inference.

Deploy generative and predictive AI models on Kubernetes with KServe’s distributed inference platform.

FedML supports distributed model training, model serving, and federated learning, with a scheduler for AI jobs across cloud and local clusters.

GPUStack manages GPU clusters for serving AI models and provides on demand GPU instances accessible through SSH.

A lightweight, portable pure C99 onnx inference engine for embedded devices with hardware acceleration support.

For Apple Silicon, Rapid-MLX offers an open-source LLM inference server and Mac app compatible with OpenAI and Anthropic APIs.

A Rust inference engine for GGUF models, Shimmy uses WebGPU and supports the OpenAI API.

bitsandbytes enables large language models in PyTorch using k-bit quantization.

OpenLLM runs open-source language models as cloud API endpoints compatible with OpenAI clients.

NobodyWho runs language models locally through an inference engine designed for efficient operation across devices.

KServe provides distributed inference for generative and predictive AI models on Kubernetes.

This Kimi API guide explains model inference billing, including token charges and cache discounts.

CTranslate2 provides a C++ and Python inference engine for transformer models.

MindSpore provides a deep learning framework for training and inference across mobile, edge, and cloud scenarios.