Join us for an exclusive series of webinars and workshops designed to enhance your AI skills and accelerate productivity, with focus on AI coding, DeepSeek, Hugging Face, GraphRAG, Intel OPEA, etc.. Whether you're building local LLMs, optimizing AI workflows, or deploying AI agents, these live sessions—led by industry experts—will provide invaluable insights and hands-on experience.

Session 3: Enabling High-Performance Execution of Graph Neural Networks on Intel NPU

Intel® AI PCs provide an ideal platform for graph neural network (GNN) workloads, with powerful acceleration from built-in neural processing units (NPUs). GNNs are crucial for tasks like Retrieval-Augmented Generation (RAG) in Large Language Models (LLMs) and event-based vision tasks. However, running GNNs involves irregular memory access and control heavy computations, leading to high inference latency. Discover how GraNNite, a hardware-aware framework developed by Intel, optimizes GNN execution on Intel NPU for unparalleled performance and efficiency. The session covers these topics:
-Demystifies GNN execution on NPUs and provides best practices to address the challenge.
-Covers the three stages to enable and optimize GNNs on NPUs.
-Explores key tools to boost performance and efficiency, including GraphSplit, EffOps, and QuantGr.
-Shows GraNNite’s improvements over default NPU execution.
- Provides insights for balancing accuracy, performance, and energy efficiency for GNN deployment.

Speakers:
- Soumendu Ghosh, Deep Learning R&D Architect at Intel
- Arghadip Das, Ph.D. student in Electrical and Computer Engineering at Purdue University

Venue:
virtual, join from anywhere.

Upcoming Sessions: