intel-arc

OpenCL is the most powerful programming language ever created. Yet the OpenCL C++ bindings are cumbersome and the code overhead prevents many people from getting started. I created this lightweight OpenCL-Wrapper to greatly simplify OpenCL software development with C++ while keeping functionality and performance.

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).

A minimal, cross-compatible CPU/GPU telemetry monitor with accurate data directly from vendor APIs and beautiful ASCII visualization.

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.

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

Arc Power is a lightweight Tuning and Management Software for Intel Arc GPUs. It is powered by IGCL, RTSS, LibreHardware Monitor and OBS.

An inference engine built with SYCL + oneDNN

Custom fan curves + GPU power/clock tuning for Intel Arc Pro B60/B70 (Battlemage) on Linux. Confirmed on Arc Pro B60 (8086:e211).

Makes Intel Arc Pro B70 GPUs actually fast on Ubuntu Server. 11 llama.cpp cherry-picks that fix the big B70 bugs (MoE slot-init SEGV, Q8_0 reorder crash, OOM reorder, missing BF16 GET_ROWS, wrong Xe2 warptile, slow K-quant DMMV, etc.) + Mesa 26 + runtime env workarounds + SYCL/Vulkan backend-selection rules. 2-7x speedup on 4x B70, bench-verified.

PosterChan AI is a Nostr-powered personal cloud and a self-hosted AI powerhouse, running on one box you own.

An alternative to Arc Control by Intel®.

Intel Arc LLM inference engine (A770/B60): Qwen hybrids up to Qwen3.8-Flash-Next (512-expert MoE through an expert cache in VRAM and host RAM), OpenVINO and llama.cpp engines, MTP speculation, prefix caching

Portable version of ComfyUI & stable-diffusion-webui for Arc B580

Plug-and-play llama.cpp runtime for Intel Arc GPUs. Auto-detects your card, picks safe SYCL defaults, and exposes an OpenAI-compatible API.

面向 DeepSeek Harness 的本地图像生成插件（优化版）：经本机 ComfyUI 调用 Qwen-Image 2.1 生成图像，全部流量限于 127.0.0.1。本版增强推理性能、NVIDIA/Intel/AMD 显卡适配与 Windows/Linux 兼容。原作者 @奇迹与你，优化版 @yanfei0725。

Linux (Arch) optimization guide for Samsung Galaxy Book6 Pro (NP960XJG) — Panther Lake, Arc B390, fingerprint, BIOS analysis, idle power 7.5W→1.9W

Comprehensive guide to AV1 encoding with Intel Arc using FFmpeg and QSV on Linux

Fan research project: the real DLSS 5 (71-block DLSSNR) neural-rendering graph running live on Intel Arc via Vulkan cooperative-matrix (XMX) cores — Vulkan / DX9 / DX10 / DX11 / DX12 games + screen mode. Demo build.

Proxmox VE GPU passthrough — recipes, scripts, and failure-mode notes (CPUID, IOMMU, WDDM).