Speculative Decoding and Efficient LLM Inference with Chris Lott
The discussion focuses on Qualcomm's efforts in advancing AI for efficient large language models (LLMs) on edge devices, emphasizing compute and bandwidth challenges, and innovative solutions like speculative decoding.
AI Engineering Pitfalls with Chip Huyen
The discussion highlights the evolving role of AI in problem-solving, emphasizing the importance of asking the right questions and the integration of AI tools in communication and research.
Evolving MLOps Platforms for Generative AI and Agents with Abhijit Bose
Capital One is leveraging AI to enhance financial services, focusing on generative AI and machine learning platforms.