Latent Space: The AI Engineer Podcast cover image

ICLR 2024 — Best Papers & Talks (ImageGen, Vision, Transformers, State Space Models) ft. Durk Kingma, Christian Szegedy, Ilya Sutskever

Latent Space: The AI Engineer Podcast

CHAPTER

Efficiency and Performance in Generative Models: Exploring FastGEN and LAMA

This chapter explores the performance and efficiency of instruction fine-tuned LAMA and the FastGEN method that utilizes adaptive KV caching. It presents experimental results on memory trade-offs and model sizes while discussing future research directions for optimizing the LAMA model.

00:00
Transcript
Play full episode

Remember Everything You Learn from Podcasts

Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.
App store bannerPlay store banner