Open-source library of optimized deep learning operations (matmul, convolution, attention) for CPUs (x64, AArch64, RISC-V) and Intel GPUs. Used by PyTorch, TensorFlow, OpenVINO, and ONNX Runtime.
-
Updated
Oct 7, 2026 - C++
Open-source library of optimized deep learning operations (matmul, convolution, attention) for CPUs (x64, AArch64, RISC-V) and Intel GPUs. Used by PyTorch, TensorFlow, OpenVINO, and ONNX Runtime.
Make use of Intel Arc Series GPU to Run Ollama, StableDiffusion, Whisper and Open WebUI, for image generation, speech recognition and interaction with Large Language Models (LLM).
🎨ComfyUI standalone pack for Intel GPUs. | 英特尔显卡 ComfyUI 整合包
End-to-end subtitle translation workstation with cloud and local OpenVINO model support.
Open recipes, engine patches, and benchmark harnesses for LLM inference on Intel Arc Pro B60/B70 (Battlemage, Xe2). MoE 35B at 160 t/s decode / 7.5K t/s prefill single-stream, 27B at 50~ t/s decode / 1.7K t/s prefill single stream. vLLM XPU MTP unlocked. Muse Glimmer recipe added!!
Benchmark results and performance data for the Intel Arc Pro B70 GPU (Xe2/Battlemage) - LLM inference, video generation, dual-GPU scaling.
Docker build scripts for TornadoVM on GPUs: https://github.com/beehive-lab/TornadoVM
Intel LevelZero JNI library for TornadoVM
A Rust operating system that runs on a real laptop: its own kernel, Intel GPU and Wi-Fi drivers, HTTPS, a Meridian desktop, and results collected from IBM's quantum hardware.
KDE Plasma Widget that displays Intel GPU usage including whether or not video acceleration is being used.
A pure C inference engine designed for Intel Xe-LP iGPUs and Gemma 4 26B-A4B QAT.
a bunch of scripts that i made to automate your task and get the best battery life
Optimize test for ultralytics yolo11. Using OpenVINO, TensorRT, and Hailo-8.
Prometheus exporter for nvtop metrics written in Python.
Fast STT proxy for whisper.cpp with OpenVINO acceleration on Intel hardware
Per-precision XMX (matrix engine) profiling for Intel Arc GPUs via Level Zero metric streamers — observes any workload without wrapping it
Gnome Shell Extension to show 3D Rendering Load, Video Acceleration Load, and Power Usage of Intel GPUs
To associate your repository with the intel-gpu topic, visit your repo's landing page and select "manage topics."