intel-npu

End-to-end subtitle translation workstation with cloud and local OpenVINO model support.

Windows-first OpenAI-compatible local LLM server powered by OpenVINO GenAI for Intel CPU/GPU/NPU, with chat UI, model conversion, and setup scripts.

Please see the newer: https://github.com/Quazmoz/openvino-windows-llm

A high-performance Docker container that runs OpenAI's Whisper model. Optimized for CPU, Intel NPU, Intel Arc/iGPU, and NVIDIA CUDA GPUs.

High-performance native local AI inference runtime platform for Intel AI PCs (100% Nim + OpenVINO)

Resonance: A Nim OpenVINO C API wrapper / binding library with Intel NPU-oriented runtime helpers.

NimVoice: fully offline local TTS in Nim with Intel OpenVINO C API, Intel NPU acceleration, and attribution to Resonance

Fast, calibrated System-1 decisions (Jev/Laya-style) on your NPU/GPU, plus per-prompt skill & MCP tool leasing that cuts agent context ~99%.

Complete guide and scripts for setup, execution and testing the AI models (ONNX) performance on NPU architectures (Qualcomm QNN & Intel OpenVINO) on Windows.

NPU-assisted real-time shader pipeline for Minecraft — Intel NPU generates budget fields, GPU renders smarter

让你电脑里那块闲置的 NPU，第一次替你的 AI 编程助手干活：按语义找代码、不占 CPU、不出网。 | Put your idle Intel NPU to work for AI coding agents - semantic code search, fully offline, zero CPU cost.

Offline speech-to-text for Pop!_OS and Ubuntu 24.04 with optional Intel NPU, Whisper, Qwen3-ASR, Parakeet, Vulkan, COSMIC Wayland overlay, and private local dictation.

Home Assistant OS add-ons: Parakeet TDT 0.6B v3 speech-to-text on the Intel NPU, and Silero v5 Russian text-to-speech on the CPU — both over the Wyoming protocol, built from source, every download SHA-256 pinned.

Benchmarking the impact of compiler-level graph optimizations on NPU inference performance and memory wall bottlenecks.

Professional benchmarking framework for Intel NPU, CPU, and GPU inference using OpenVINO

Intel NPU voice dictation - 纯NPU本地语音听写

Create the impossible middle—robot → dog and any A→B transformation—locally on Intel NPU + Arc GPU.

Local Whisper transcription to SRT/TXT on the Intel NPU

On-device Whisper dictation on Intel NPU for GNOME / Ubuntu Wayland

Getting a Samsung Galaxy Book4 Ultra (NP960XGL) fully working on CachyOS — webcam (IPU6/OV02C10), fingerprint (SDCP), NPU, battery limit, suspend. The reasoning, not just the commands.