Evaluation of LLMs and Scale GNN training

We have invited two guests to cover two different topics. Please register at our event partner AICamp to obtain Zoom link

https://www.aicamp.ai/event/eventdetails/W2024053109

Agenda:
9:00 am -- 9:05 am PST members join online
9:05 am -- 9:45 am PST Talk 1
9:45 am -- 10:15 am PST Talk 2
10:30 am PST event closed

Talk 1: Training GNNs at Internet Scale using cuGraph and WholeGraph
We present our approach to manage 70TB graph datasets, and train GraphSage across 1024 GPUs. One key feature of our approach is the separation of the graph sampling and GNN training phases, giving the user flexibility to scale each independent of the other. WholeGraph provides a distributed feature store that leverages GPU memory and caching to provide high performance dataloading. Dataloading and sampling are the two largest bottlenecks in GNN training according to our profiling.

Speaker: Joe Eaton (NVIDIA)
Joe Eaton is a Distinguished System Engineer for Data and Graph Analytics at NVIDIA, and is currently leading the company strategy for Graph Neural Networks at Nvidia. Joe leads teams for code optimization, graph analysis, framework development and optimization,
as well as interacts with prospective customers in industry.
Key areas of interest are financial services, retail Recommenders, and molecular generation for drug discovery.

Talk 2 : Practical Evaluation of LLMs and LLM Systems: Ensuring Relevance and Effectiveness in Real-World Applications

In-Depth Analysis of LLM Evaluation Methods: Gain insights into various methods used to evaluate LLM models, understanding their strengths and weaknesses.

End-to-End Evaluation Techniques: Explore how LLM augmented systems are assessed from a holistic perspective, ensuring comprehensive evaluation. Pragmatic Approach to System Deployment: Learn practical strategies for applying evaluation techniques to real-world systems, ensuring seamless deployment and functionality.
Focused Overview on Critical LLM Aspects: Get an overview of essential evaluation techniques for assessing crucial elements of modern LLM systems, enhancing understanding and applicability.
Simplifying the Evaluation Process: Understand how to streamline the evaluation process, making the work of LLM scientists more efficient and productive.

Speaker Andrei Lopatenko

Andrei Lopatenko is an accomplished technology expert with over 18 years of experience in the industry. He earned a PhD in Computer Science from the University of Manchester and has been a key player in various high-profile AI projects at leading companies such as Google, Apple, Walmart, eBay, and Zillow. His notable work includes developing essential components of Google's search engine, initiating Apple Maps Search, and leading significant AI and search initiatives at Apple, Walmart, eBay, and Zillow. Additionally, Andrei co-founded a Conversational AI startup that was acquired by Facebook/Meta

