AWS explains how to measure autoscaling targets for SageMaker TTS
What happened
On 23 October 2026, the AWS Machine Learning Blog published a post addressing the problem of guessing autoscaling target values for self-hosted TTS endpoints. It describes deploying the 82-million-parameter Kokoro-82M model on an Amazon SageMaker AI real-time endpoint and using measured Q_max (the highest concurrency a single instance can sustain within the SLO) and T_total (the end-to-end time of one scale-out) to derive the scale-out threshold, the scale-in threshold and two cooldown periods.
Written by AI from the reports · updated 3 h ago
Timeline
Follow the reports to see the event from each side.
- AWS Machine Learning BlogStop guessing auto scaling targets for TTS on Amazon SageMaker AI
Teams deploying custom text-to-speech models on Amazon SageMaker AI often guess at autoscaling thresholds, and a wrong guess either wastes GPU spend or breaches a latency SLO. This post deploys Kokoro-82M as a custom container and derives a measured autoscaling policy from two live-endpoint measurements, Q_max and T_total, instead of guesswork.
Heat of this event
Current heat 9·Peak in the comparable range 9（Oct 23 03:00）·Change over 24 hours in the comparable range –
The trend compares only the same accounts observed without a break, so its range can be narrower than the current heat count. Move the pointer or tap the chart to see each hour; with a keyboard, use the left and right arrow keys.