Here is a list of event, includes speaker session and other intermediate slots (e.g. lunch):
This chalk talk delves into optimizing and deploying large language models (LLMs) at scale. Explore large model hosting, optimization techniques, model partitioning, batch processing, and model fine-tuning.
The speaking section will explore AWS's open-source projects in the container realm. Attendees will learn about tools that enable fast, secure, and scalable application development to meet enterprise needs. The session will highlight Finch, a new open-source container tool that streamlines the container development process. Additionally, the discussion will cover Bottlerocket, a Linux-based open-source operating system that reduces maintenance overhead and enhances security. The speaker will also introduce other AWS open-source projects that tech enthusiasts may find interesting.
"On March 29, 2024, Andres Freund, a Microsoft software developer, emailed Openwall informing the community of the discovery of an SSH backdoor in XZ Utils 5.6.0 and 5.6.1 (CVE-2024-3094). XZ Utils is a suite of open-source software that provides developers with lossless compression. The tool is very widely distributed as it comes installed by default on most Linux distributions and macOS systems.
Have you ever wondered how large organizations and high tech unicorns are able to build platforms on Kubernetes to run all kinds of workloads - web, stateless, stateful, batch, and even AI?
Kubernetes’ strengths in dynamic resource scheduling, automated orchestration and vibrant ecosystem of frameworks make it ideal for building AI/ML platforms. This becomes highly scalable when it combines the power of GKE hosted in the Cloud with disposable GPUs and TPUs.
In the rapidly evolving field of artificial intelligence, mastering Large Language Models (LLMs) requires a blend of optimization, graph technology, and Retrieval-Augmented Generation (RAG) techniques. This talk introduces key strategies for maximizing LLM performance, integrating graph databases, and advancing RAG methodologies. We’ll delve into topics such as optimization flows and prompt engineering while also examining the synergy between LLMs and graph technology through knowledge graphs and vector searches.
In this session you will learn about how you use Large Language Model such as OpenAI and Cohere to get information out of data stored in MySQL. We will explore how you can use the popular open source framework, LangChain to quickly build a Q&A system to answer questions on MySQL data.