Charles Packer on MemGPT - Weaviate Podcast #73!
Weaviate Podcast
Ideal running speed of a meta model and working with billion parameter models
This chapter explores the challenges and solutions for achieving the ideal running speed in high parameter models, including the benefits of using quantized models and running parallel models for faster decoding speed.
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.
