The Intel® Gaudi® 2 AI accelerator has emerged as a game changer for AI compute, built from the ground up to accelerate generative AI and large language models (LLM). (Per the latest MLPerf* Training v4.0 benchmark, it remains the only MLPerf-benchmarked alternative to the NVIDIA* H100 for training and inference.¹)

This session unpacks three ways to get started with Intel Gaudi 2 AI accelerators to supercharge your LLM-based applications with performance, productivity, and efficiency, so you can:

• Run LLMs with Hugging Face* Transformer models for training.
• Run inference on generative AI (GenAI) models using Hugging Face* for Optimum Habana.
• Migrate your models from a GPU environment to Intel Gaudi 2 AI accelerators with just a few lines of code.

Skill level: Intermediate

• The Docker* image for Intel Gaudi AI accelerators contains all the software needed to run your models.

• Model References for Intel Gaudi AI Accelerators
• Hugging Face: Optimum Habana
• GPU Migration Toolkit

1 Intel Gaudi 2 AI Accelerators Enable a Lower-Cost Alternative for AI Compute and GenAI