ipex

A LLaMA2-7b chatbot with memory running on CPU, and optimized using smooth quantization, 4-bit quantization or Intel® Extension For PyTorch with bfloat16.

[ISCA'25] LIA: A Single-GPU LLM Inference Acceleration with Cooperative AMX-Enabled CPU-GPU Computation and CXL Offloading

Intel® AI Inference Samples provide example code for deploying optimized inference in Intel platforms.

FliX is an Integrated Firmware for DitroniX Power Energy Monitor SDK Boards

Collection of AI Containers - Prebuilt and Ready-to-Use

llama.ccp on Intel Arc Battlemage, that actually works

PHP Library for interaction with restapi.ipex.cz

Docker Compose stack for serving a local, OpenAI-compatible LLM (vLLM on Intel XPU) on an Intel Arc Pro B60 GPU — reproducible config with operator and developer docs.

Container stack for Ollama, ComfyUI, SD.Next, and Whisper optimized for Intel Arc GPUs via SYCL and IPEX

Ipex ⛗ AbraFlexi integration

A collection of docker compose files that can spin up an openwebui / ollama stack for Intel and AMD cards. Tested on both Intel Arc A770 and Radeon RX 6650 XT cards.

The Gen AI Hackathon project aims to utilize machine learning for healthcare by developing a web application that can detect various diseases such as asthma, cancer, diabetes, and stroke. The application provides real-time diagnosis based on predictive modeling.