View the webinar’s recording as we discuss the cutting-edge capabilities of the Habana® Gaudi®2 AI processor in capturing the potential of Generative AI and Large Language Models (LLMs).
Key Highlights & links:
- 7:51 to 8:46 – Model References
- 9:07 to 9:27 – Stable Diffusion Demo
- 13:30 to 13:50 – GPU Migration Demo
- 17:56 to 18:16 – GPU Migration Toolkit
- 27:01 to 27:21 – Hugging Face Demo
- 33:18 to 33: 38 – Documentation
As the world of artificial intelligence continues to push boundaries, Gaudi2, Habana’s advanced deep learning accelerator, has emerged as a game-changing solution. In this webinar, our team of experts will guide you through the steps to easily enable Gaudi2 to supercharge your LLM-based applications with performance, productivity and efficiency.
Key Topics Covered:
- Introduction to Gaudi2 AI Processor: Gain a comprehensive understanding of the Gaudi architecture, and how to take advantage of Habana’s large catalog of optimized models.
- Model Migration: We’ll show you how to quickly migrate models from other platforms with the addition of only a few lines of code.
- Accelerating LLM Training: Discover how Gaudi2 uses DeepSpeed and Hugging Face-based models to accelerate LLM training, including fine-tuning a model from the Hugging Face Optimum Habana repository.
- High-Performance Inference: Learn how Gaudi2 can deliver lightning-fast, real-time generative AI and LLM inference results.
Whether you’re a data scientist, AI researcher, developer, or technology enthusiast, this webinar will equip you with the knowledge and insights necessary to tap into the benefits of the Gaudi2 AI processor and empower your LLM-based projects with unparalleled speed and efficiency.
Featured Speakers
Greg Serochi
Developer Advocate and Applications Engineering
