Tutorials and Examples

Explore resources for developing and running AI workloads on Intel® Xe GPUs, including working demos and solution-planning guidance.

  • Intel AI Software Catalog: Discover and plan AI solutions for Intel platforms, including LLM inference, assistants, RAG, computer vision, and multimodal AI.

  • Intel XPU AI Demos: Explore AI use cases that run locally or in the cloud on Intel XPU using open-source inference runtimes such as vLLM and SGLang in Docker, or PyTorch XPU. The demos have been validated on Intel® Arc™ Pro B-Series.

  • Intel XPU Full-Stack Monitoring: Monitor GPU, CPU, and vLLM inference metrics on Intel XPU hosts in real time with preconfigured Grafana dashboards. Deploy the monitoring stack using Docker Compose.