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.

NUMA-distributed weight banking for LLM inference on IBM POWER8. 147 t/s (8.8x stock). Part of the Proof of Physical AI stack.

llama.cpp optimizations for IBM POWER8: vec_perm non-bijunctive collapse, PSE hardware entropy, DCBT prefetch. Sovereign inference. Part of the Proof of Physical AI stack.

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.

Benchmark results and performance data for the Intel Arc Pro B70 GPU (Xe2/Battlemage) - LLM inference, video generation, dual-GPU scaling.

MOTO - Autonomous ASI Deep Research Harness by Intrafere - creative novelty-seeking researcher with autonomous Lean 4 proof generation. For S.T.E.M. users; run for days at a time once pressing start - no interaction needed! Agents working in parallel from either local host LM studio, OpenRouter, or both. No internet required. Star us for more!

A Distributed Engine for AI

GPU-aware inference mesh for large-scale AI serving

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

Unity TTS plugin: Piper neural synthesis + pure C# G2P (6 languages: ja/en/zh/es/fr/pt) + Unity Inference Engine. Windows/Mac/Linux/Android/iOS/WebGL ready. High-quality voices for games & apps.

Hands-on course materials for deploying and optimizing generative AI on Arm processors: Raspberry Pi, AWS Graviton, SIMD, quantization (educational)

A framework for performing AI model inference on encrypted data.

Save 50% off GenAI costs in two lines of code

World's first L1 blockchain with deterministic on-chain AI inference verified through multi-node consensus. Bitwise identical outputs across every chip, every architecture.

A development framework for Fully Homomorphic Encryption (FHE)

EvoLink.ai - One Key, All AI Models