AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
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.