Modal API and Serverless GPU Compute | 4min snip from Weaviate Podcast

Instructor with Jason Liu - Weaviate Podcast #88!

Weaviate Podcast

CHAPTER

Modal API and Serverless GPU Compute

Discussion on the capabilities of the modal API for serverless GPU compute, including defining the function 'inbed' and using modal for batch tasks. Mention of using GPUs for vector search and NVIDIA Rapids' KAGRA library. Mention of using GPUs as databases for faster data transfer speeds.

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.