# inference-engine

Local-first auditable AI agent workspace and append-only runtime

Apache Maka is an open-source, local-first AI agent workspace under the Apache Software Foundation that uses an append-only event log to record model messages, tool calls, and permissions for deterministic session replay and auditability.

Interactive architecture diagram and visual delta engine for AI agents

Archify is an open-source AI agent skill with 37,000+ GitHub stars that compiles typed JSON intermediate representations into interactive, animated system architecture diagrams with motion and visual delta diffs for Claude Code and Cursor.

Heterogeneous CPU-GPU inference and SFT for large MoE models

Open-source framework for running and fine-tuning large Mixture-of-Experts models with heterogeneous CPU-GPU execution, optimized kernels, limited VRAM and SGLang or LLaMA-Factory integrations.

Open-source toolkit for quantizing, deploying, and serving LLMs and vision-language models

LMDeploy is an Apache-2.0 toolkit for self-hosting LLM and vision-language model inference with TurboMind and PyTorch engines. It combines continuous batching, blocked KV cache, tensor parallelism, AWQ and KV-cache quantization with OpenAI-compatible APIs, multi-GPU distribution, offline pipelines, and production metrics.

Lightweight mobile and edge AI inference engine

MNN is a lightweight, high-performance deep learning inference engine developed by Alibaba and battle-tested across 30+ Alibaba apps including Taobao, DingTalk, and Youku. It supports TensorFlow, ONNX, PyTorch, and Caffe models with optimized backends for CPU, GPU, and NPU on mobile and edge devices. MNN includes on-device LLM inference, an OpenCV-like image processing library, and Python bindings for rapid prototyping. Apache 2.0 licensed with 15K+ stars.

High-performance mobile neural network inference

NCNN is Tencent's high-performance neural network inference framework optimized for mobile and embedded platforms. It features pure C++ with zero dependencies, ARM NEON assembly optimization, Vulkan GPU acceleration, and sophisticated memory management for minimal footprint. Supports importing models from PyTorch, ONNX, Caffe, TensorFlow, and Keras with 8-bit quantization and half-precision storage for efficient on-device deployment across Android, iOS, and Linux.

Cross-platform on-device AI model runtime

Nexa SDK enables running frontier LLMs and multimodal models locally across PC, mobile, IoT, and wearables with automatic hardware acceleration for GPU, NPU, and CPU. It supports Qwen, Gemma, Llama, DeepSeek models with Python/C++ desktop SDKs, Android/iOS mobile SDKs, and Docker for edge deployment. Includes an OpenAI-compatible API server with chat and function calling support.

Cross-platform high-performance ML inference engine

ONNX Runtime is Microsoft's open-source inference engine for machine learning models in ONNX format. It delivers cross-platform acceleration via execution providers for NVIDIA CUDA, TensorRT, DirectML, CoreML, OpenVINO, and more. Supports training acceleration, quantization, and GenAI workloads. Used in production across Windows, Azure, Office 365, and thousands of applications with pip-installable Python and native C++/C#/Java APIs.

Intel's open-source AI inference optimization toolkit

OpenVINO is Intel's open-source toolkit for optimizing and deploying AI inference across CPUs, GPUs, and NPUs. It supports models from PyTorch, TensorFlow, ONNX, and TFLite, providing graph optimizations, quantization, and hardware-specific acceleration. The toolkit includes a GenAI API for LLM deployment and runs on Intel, ARM, and x86 platforms for edge, desktop, and cloud inference workloads.

On-device AI inference for React Native apps

Declarative framework for running AI models on-device in React Native applications, powered by Meta ExecuTorch runtime. Supports LLMs including Llama 3.2, computer vision, OCR, embeddings, and vision-language models on iOS 17+ and Android 13+. Developed by Software Mansion with pre-built optimized models, custom model export support, and privacy-first inference without any cloud dependency for mobile AI development.

Edge AI deployment SDK for heterogeneous SoCs

Roofline AI is a contact-sales edge AI deployment toolkit built around an MLIR- and IREE-based compiler. Its SDK compiles models ahead of time, a lightweight C runtime executes them across CPUs, GPUs, and NPUs, and a performance dashboard tracks latency, throughput, memory use, and model coverage across devices.

Cross-platform on-device AI inference SDK

RunAnywhere SDK is a production-ready toolkit for running AI models entirely on-device across iOS, macOS, Android, Web, React Native, and Flutter. It provides a unified C++ core with platform-specific bindings for LLM text generation via llama.cpp, vision-language models, Whisper speech-to-text, Piper text-to-speech, and on-device image generation. All processing stays local with zero cloud dependency, ensuring privacy and low latency for mobile and edge AI applications.