AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
3min chapter
🤹♀️ Building models that actually perform with Kyle Gallatin
The MLOps Podcast
Is It the Platform Team or the Data Scientist?
Lake: There's a lot of things that could happen within juste model itself to introduce latency. We're actually working on an inhouse on framework right now to identify that as early in the pipe line as possible, almost at the training and experimentation side. A simple nested fore loop, instead of more vectorized code, has led from like 200 mill a second p 99 ladency going down to like 15 mill aSecond p 99 latency,. And it's those kinds of things youre while like there are little things you can do in your code that really just have a huge, huge impact on how mol runs of production.
00:00
Transcript
Episode notes
Get the Snipd
podcast app
Unlock the knowledge in podcasts with the podcast player of the future.
AI-powered
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