NVIDIA Developer Day with Scaleway
Tuesday, June 11, 2024, 09:00 a.m. CEST
Tuesday, June 11, 2024, 09:00 a.m. CEST
Let’s talk about some of the most recent AI use cases. We’ll discuss how to choose the most appropriate NVIDIA infrastructure available at Scaleway. We’ll explore options from standalone solutions to clusters and examine how to accelerate the corresponding workloads.

Javier is a Senior Solutions Architect for High Performance Computing (HPC) and Cloud Service Providers (CSP) at NVIDIA. He helps customers to clearly identify their use case and proposes end-to-end solutions to accelerate the corresponding workloads. His background is in networks and infrastructure cybersecurity. He specializes in demonstrating how we build clusters of GPUs at NVIDIA. Prior to NVIDIA, he worked as post-sales at Fortinet and at ISP such as Telefonica and Orange.

With 25+ years of experience in Digital products, Fabien Da Silva is AI Product Manager in Scaleway, in charge of the GPU instances, HGX as a service clusters and other AI hardware accelerated products. With a Master Degree in Engineering, his experience at different positions in IT, management and Innovation, grew his passion for Deep Learning and lead him to focus on harnessing the power of AI . He works to make AI responsible, efficient and accessible to all.
Tuesday, June 11, 2024, 10:00 a.m. CEST
We’ll discuss how to use Scaleway’s LLM inference tool to easily deploy open-source large language models (LLMs) on NVIDIA GPUs. This session will introduce you to the fundamentals of retrieval-augmented generation (RAG) architectures and demonstrate how the LLM inference service facilitates the deployment of these models by fully managing the underlying infrastructure.
We’ll also cover the technical details of integrating NVIDIA’s TensorRT-LLM and Triton technologies, designed to optimize LLM performance. Learn how these advances can be integrated into your projects to enhance AI content generation, while ensuring security and compliance in a secure European cloud environment.

Dora Csillag is a Senior Solutions Architect at NVIDIA. She helps customers to build and deploy AI solutions, while focusing on Inference in the field of Computer Vision and generative AI. She was previously an Applied Researcher in Video Analytics, for Road Safety, Border Controls, and other industries. With over a decade's expertise in the creation of digital products, Frédéric Bardolle is Lead Product Manager AI at Scaleway. With a PhD in machine learning, his career path has taken him from tech startups in fields as diverse as edtech, cryptography and web3, to the public sector. He notably built the Ministry of the Armed Forces' digital services incubator. Co-founder of Data for Good in 2016, he works to align technology with societal issues, prioritizing privacy and data protection.

Sebastian has over 15 years of experience in GPU-driven image processing solutions. He helped create the first Digital Intermediate pipeline in Mexico City, then moved on to work on real-time color grading and transcoding systems, training teams in Tokyo, Moscow, Bucharest and Paris. Now, he is dedicated to making Scaleway the leading European platform for AI and HPC solutions.
NOT IN USE
Tuesday, June 11, 2024, 11:00 a.m. CEST
We’ll share how to choose the right path for your AI initiatives. Staring with the importance of understanding the key metrics in large language model (LLM) inference sizing. This talk will equip you with essential tools to optimize performance by dissecting LLM inference benchmarks and comparing configurations. We’ll demonstrate how NVIDIA’s software ecosystem can be leveraged to elevate your AI applications by supporting various layers of abstraction for inference. We’ll share best practices and tips to allow you to bring unmatched efficiency and effectiveness to your LLM inference projects.

Dmitry Mironov is an AI Solutions Architect at NVIDIA. He helps customers use GPUs efficiently. Currently he is mainly focused on LLM Inference benchmarking and NVIDIA NIM. Before NVIDIA, Dmitry served as a CTO and Co-founder of a startup. He had been integrating Computer Vision into gold mining, transportation, energy and other industries.
NOT IN USE
NOT IN USE
In this session, we'll answer any additional questions that attendees may have, beyond those discussed during the sessions.



Select one or more of the following sessions and complete registration.
Click any session listing in the registration form to view its details.
By filling out the form, you agree to share your data with our partner, Scaleway. I understand that my information will be handled in accordance with Scaleway’s privacy policy.
Content goes here
content goes here

Webinar: Description here
Date & Time: Wednesday, April 22, 2018