Search – talk-data.com

Title & Speakers	Event
Event AI Meetup: Vector DB and Benchmarking Framework for LLama 2024-05-15
Vector database: A technical deep-dive 2024-05-15 · 17:00 JP Hwang – Technical Curriculum Developer @ Weaviate In this session, we'll discuss how data is stored, retrieved, augmented and isolated for users, and how index types, quantization, multi-tenancy, sharding, and replication affect their behaviour and performance. We will also discuss vector databases' integration with AI models that can generate vectors, or use retrieved data to produce augmented, or transformed outputs. When you emerge from this deep dive, you will have seen the inner workings of a vector database, and the key aspects that make them different to your grandma's database. weaviate vector databases ai models index types quantization multi-tenancy sharding replication
Unveiling BeFOri: New Benchmarking Framework for LLama 2024-05-15 · 17:00 In this session, we'll explore how BeFOri enhances performance benchmarks and drives advancements in AI model efficiency. BeFOri, the benchmarking framework is designed to optimize and evaluate LLama2 and LLama3 models on Nvidia V100s and H100 chips. befori llama2 llama3 nvidia v100 nvidia h100 benchmarking framework