inference-server

LLM inference server with continuous batching & SSD caching for Apple Silicon — managed from the macOS menu bar

⚡ Pure-Rust WebGPU inference engine — OpenAI-API compatible, GGUF native, runs on any GPU. No Python. No llama.cpp. Single binary.

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.

Open-source inference server and production cluster for all the models your agent needs.

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

High-performance OpenAI and Anthropic compatible LLM inference server for Apple Silicon. Native MLX, continuous batching, multimodal models, MCP tool calling, and Claude Code support.

The simplest way to serve AI/ML models in production

TurboOCR, >200 img/s OmnidocBench. TensorRT FP16, PP-OCRv6, HTTP + gRPC

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

PMetal: high-performance Apple Silicon framework for local LLM inference, LoRA/QLoRA fine-tuning, serving, quantization, and MLX/Metal acceleration.

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

Self-hosted, OpenAI-compatible inference for the agentic era: reasoning LLMs, universal tool calling, and the Responses API alongside embeddings, speech, and image models — many models sharing your GPUs, one gateway. Powered by Ray Serve.

Local inference server for Apple Silicon — hot-swaps MLX models (LLM, vision, embeddings, TTS, STT) via OpenAI API

vLLM + Qwen3.6-27B (BF16) OpenAI-compatible inference server on AMD Strix Halo (Ryzen AI Max+ 395, gfx1151). Vision input, 256K context, /v1/responses with separated reasoning, via TheRock ROCm.