3min chapter

MLOps.community  cover image

Racing the Playhead: Real-time Model Inference in a Video Streaming Environment // Brannon Dorsey // Coffee Sessions #98

MLOps.community

CHAPTER

Keeping Workloads Out of the Cluster

Good m l ops, in a lot of ways, starts with good devops. And i think we can borrow some of the ideas that devops has e, when we think about imals,. Right? I'm partially intacting a bias, cause i'm come at a lot of engineering from this devops background and i find s interesting. E so i really like the idea f like keeping state out of the cluster. So you could use, i like, a manage data by service like r d s. If your data is a fits nicely in a relational data base, you could use a object storage - things like that. And then have your work loads kind of, like,

00:00

Get the Snipd
podcast app

Unlock the knowledge in podcasts with the podcast player of the future.
App store bannerPlay store banner

AI-powered
podcast player

Listen to all your favourite podcasts with AI-powered features

Discover
highlights

Listen to the best highlights from the podcasts you love and dive into the full episode

Save any
moment

Hear something you like? Tap your headphones to save it with AI-generated key takeaways

Share
& Export

Send highlights to Twitter, WhatsApp or export them to Notion, Readwise & more

AI-powered
podcast player

Listen to all your favourite podcasts with AI-powered features

Discover
highlights

Listen to the best highlights from the podcasts you love and dive into the full episode