Baseten adds autoscaling schedules to cut cold-start delays for predictable traffic
Overview
Baseten has added autoscaling schedules that raise a deployment's minimum number of replicas before predictable traffic arrives, according to its blog post.
Schedules can recur, such as every weekday morning, or run once ahead of a launch, and the post says this reduces cold-start delays. Each environment supports up to 10 schedules, which can be set in the dashboard, through the CLI, or via the Management API.
Written by AI from the articles below · updated Oct 30, 1:49 PM ET
Check the sources:
Article timeline
The articles in this story. Times are ET.
- Baseten BlogOfficialBaseten adds autoscaling schedules to cut cold-start delays for predictable traffic
AIBaseten's autoscaling schedules raise the minimum number of replicas before predictable traffic arrives, reducing cold-start delays. Schedules can recur, such as on weekday mornings, or run once ahead of a launch. Each environment supports up to 10 schedules, configured through the dashboard, CLI, or Management API.
Heat Trend
Not enough continuous observations to show a trend yet.