The easiest way to serve AI apps and models - Build Model Inference APIs, Job queues, LLM apps, Multi-model pipelines, and more!

Extension for Scikit-learn is a seamless way to speed up your Scikit-learn application

oneAPI Data Analytics Library (oneDAL)

The easiest way to use Machine Learning. Mix and match underlying ML libraries and data set sources. Generate new datasets or modify existing ones with ease.

Cross-platform c++ sdk & model hub for cross-platform AI inference. Ready-to-deploy models including Segment Anything 3, Depth Anything 2 and Gemma.

High-Performance AI-Native Web Server — built in C & Assembly for ultra-fast AI inference and streaming.

Client library to interact with various APIs used within Philips in a simple and uniform way

GPU-aware inference mesh for large-scale AI serving

Unity TTS plugin: Piper neural synthesis + OpenJTalk Japanese + Unity AI Inference Engine. Windows/Mac/Linux/Android/iOS ready. High-quality voices for games & apps.

MOTO - Autonomous AI Deep Research Harness - A high-risk high-reward (novelty seeking) mathematics researcher for S.T.E.M. users, run for days at a time once pressing start - no interaction needed! MOTO uses simultaneous agents working in parallel from either local host LM studio, OpenRouter, or both. Star us and follow - there's more to come soon!

Customed version of Google's tflite-micro

A powerful, faster, scalable full-stack boilerplace for AI inference using Node.js, Python, Redis, and Docker

KaiROS AI— Intelligence, Precisely When It Matters.

A personal demo project for Flutter + ONNX Runtime integration. Not related to any company work.A comprehensive on-device face recognition SDK for Flutter

Dockerized Yawcam-AI, Edge-ready AI NVR with CPU and CUDA builds, RTSP support, persistent storage, YOLO inference, and EdgePulse optimization.

Arbitrary Numbers

🌱 Intelligent IoT greenhouse fan controller using AI/ML for automated climate control. Features ESP32 + DHT22 sensors, real-time Firebase integration, Flutter mobile app with TensorFlow Lite on-device inference, and Wokwi simulation. Complete full-stack solution demonstrating IoT + AI integration.

Distributed Inference Key-value Cache in Cloud Setting

llama.cpp with native AMD RDNA4 (gfx1201) ROCm 7.11 support - 98.97 tok/s AI inference, competitive with RTX 4070 Ti, 32GB VRAM

A comprehensive framework for multi-node, multi-GPU scalable LLM inference on HPC systems using vLLM and Ollama. Includes distributed deployment templates, benchmarking workflows, and chatbot/RAG pipelines for high-throughput, production-grade AI services