Multi-Decode - Part 2

This week we continue our discussion on the work that Ted and Roger have done on Multi-Decode. Multi-Decode leverages custom 4D masking and custom RoPE embedding to simultaneously and efficiently generate multiple decoding sequences per inference step using a single KV cache. Beam search and optimized writing-in-the-margins will be two use cases we will discuss. Come and join in the discussion and the brainstorming.

The prior Meetups will be available on our YouTube channel, west coast machine learning - YouTube

Every week we meet (virtually) and discuss the most interesting topics in AI, ML, and Deep Learning.

We usually rotate weeks so that every other week one of the members presents a deep learning/machine learning paper, frequently paired with a video explaining the concepts. In the off weeks, we present information about different projects. We cover computer vision, language (LLM's), health/hard science, and generative models (Diffusion, GAN's etc.).

People of all levels of skill are welcome--from newbies to machine learning, to PhD's in DL/ML/AI.

We have been meeting for over 7 years weekly and have developed a neat pace and community--and all are welcome. Come join us and stay abreast of the biggest topics in Artificial Intelligence.