WORKSHOP
From Concept to Code: Accelerating Generative AI Performance
20th OCT 2023 | 03:30 PM to 05:00 PM
Venue: Workshop Room 1, NIMHANS Convention Centre, Bangalore
This workshop delves into the challenges faced in AI development and model deployment across various hardware. It introduces OpenVINO as a solution, showcasing its potential in accelerating Generative AI tasks. Attendees will explore the developer journey with OpenVINO, gaining insights into overcoming deployment hurdles. A hands-on demonstration on stable diffusion with OpenVINO will underline its efficacy in enhancing Generative AI performance, providing a practical understanding of translating conceptual AI models into optimized, deployable solutions. Through this interactive session, participants will grasp how OpenVINO acts as a catalyst in bridging the gap between AI development and seamless deployment.
Anisha Udayakumar
AI Software Evangelist (APJ), Intel
- This workshop is designed for AI developers, data scientists, and technical enthusiasts who are keen on advancing their knowledge in Generative AI and model deployment. Both novices and experienced professionals can benefit from the insights provided. It's an excellent opportunity for those interested in leveraging the power of OpenVINO to accelerate the performance of AI models, especially large language models, in a variety of hardware environments.
- An in-depth discussion on challenges in AI development and deployment across different hardware.
- Introduction to OpenVINO and its advantages in accelerating Generative AI tasks.
- An exploration of the developer journey with OpenVINO, highlighting solutions to common deployment hurdles.
- Hands-on demonstration on accelerating a stable diffusion model with OpenVINO.
- Techniques for translating conceptual Generative AI and large language models into optimized, deployable solutions.
- Engaging discussions and Q&A sessions to address queries and foster a collaborative learning experience.
- The prerequisite for attending this workshop is the installation of OpenVINO on the attendees' machines. It's essential to have this setup done prior to the workshop to ensure an uninterrupted and fruitful hands-on experience. Kindly adhere to the installation steps delineated in the OpenVINO Installation Guide for your respective operating system.
Benefits/Takeaways of this workshop for the attendees
- A comprehensive understanding of OpenVINO’s capabilities in accelerating Generative AI models.
- Practical experience in optimizing and deploying a Generative AI model with OpenVINO.
- Insights into overcoming common deployment challenges faced in the AI development lifecycle.
- Networking opportunities with fellow developers and experts in the AI community.
- Enhanced readiness to translate conceptual AI models into deployable solutions, particularly in the realm of Generative AI and large language models.
Process of Swags distribution:
The swags will be distributed towards the end of the workshop. Attendees who actively participate, ask questions, and complete the hands-on session will be prioritized for swag distribution. Additionally, we will have a social media engagement activity where attendees can share their workshop experiences with a designated hashtag to be eligible for additional swags.