From Generative Models to Optimized Inference with Intel®

10 AUGUST 2024 | 09:30AM - 01:00PM | location Intel Campus: RMZ Ecospace campus, Building 2A & 2B, Marathahalli-Sarjapur ORR, Devarabeesanahalli, Bellandur, Bangalore-560103

About the workshop

Explore the evolution of Generative AI, enterprise applications, and the hardware essentials for large language models. Delve into Intel's AI-enhancing technologies, from Xeon® and Gaudi® AI Accelerators to the Core Ultra series. Engage in hands-on sessions optimizing inference and deploying AI models on Intel® Developer Cloud.

video thumbnail

Instructor

speaker image

Anish Kumar

AI Software Engineering Manager
company logo

Modules

  1. Evolution of Generative AI
  2. How do you use Generative AI models in an Enterprise use case?
  3. Need to understand how the Large Language Model works from a hardware perspective.
  4. Discuss fine-tuning and RAG for Enterprise.
  5. Factors Influencing Generative AI for Enterprise.

  1. Discuss Intel® Xeon® Features for improving performance of Generative AI workloads
  2. Discuss Intel® Gaudi® AI Accelerators for Deep Learning
  3. Discuss Intel® Core Ultra series processor capabilities for AI applications
  4. How to optimize Deep learning and Classical AI/ML applications using Intel® oneAPI AI Analytics Toolkit

  1. Introduction to Intel® Developer Cloud
  2. Optimize LLM Inference with oneAPI
  3. Showcase Stable Diffusion Inference on Intel® hardware 
  4. Implement RAG with Open LLMs like Llama 2

  • Basic understanding of machine learning and deep learning concepts
  • Familiarity with Python programming
  • Basic knowledge of natural language processing (NLP) principles
  • Understanding of neural network architectures, especially transformers
  • Familiarity with large language models (LLMs) and their applications
  • Basic knowledge of hardware components and their impact on AI performance
  • Experience with cloud computing environments (nice to have)
*Note: These are tentative details and are subject to change.

*Attendees do not need to bring their own laptops, INTEL will provide laptops for the lab.

*Attendees must carry their DataHack Summit badge to the Workshop.

*A government ID proof is mandatory for entry into the Workshop.

*By submitting this form, you confirm that you are 18 years of age or older. Intel may contact you for marketing-related communications. To learn about Intel's practices, including how to manage your preferences and settings, please visit Intel's Privacy and Cookies notices.

Stay informed about DHS 2025

We use cookies essential for this site to function well. Please click to help us improve its usefulness with additional cookies. Learn about our use of cookies in our Privacy Policy & Cookies Policy.

Show details