Speed of Light Inference w/ Modular + Data Curation/Visualization w/ NVIDIA CuML

Zoom link: https://us02web.zoom.us/j/82308186562

Talk #0: Introductions and Meetup Updates
by Chris Fregly and Antje Barth

Talk #1: Speed of Light Inference w/ NVIDIA and AMD GPUs using the Modular Platform by Abdul Dakkak @ Modular
This technical presentation will demonstrate how the Modular platform can be used to scale AI workloads across various clusters. It will delve into the collaborative functionality of the Modular stack, encompassing Modular Cloud (a cluster-level solution), MAX (the framework and runtime), and Mojo (the programming language). Together, these components deliver exceptional performance and significantly reduce Total Cost of Ownership (TCO) across both NVIDIA and AMD GPU architectures.

Talk #2: Advanced and Accelerated Data Curation and Visualizations for LLMs with NVIDIA CuML, DBSCAN, and tSNE (Performance-focused) by Theo Viel and Dante Gama Dessavre @ NVIDIA
This technical talk will focus on applying high-performance techniques to data curation and visualization tasks for LLMs with NVIDIA cuML by AI performance specialist Theo Viel. It will also include a performance deep dive on CUDA-X library cuML and why GPUs excel at boosting performance for DBSCAN and tSNE algorithms with ML engineering and AI Infrastructure manager Dante Gama Dessavre.

Zoom link: https://us02web.zoom.us/j/82308186562

Related Links
Github Repo: http://github.com/cfregly/ai-performance-engineering/
O'Reilly Book: https://www.amazon.com/Systems-Performance-Engineering-Optimizing-Algorithms/dp/B0F47689K8/
YouTube: https://www.youtube.com/@AIPerformanceEngineering
Generative AI Free Course on DeepLearning.ai: https://bit.ly/gllm