Merge pull request #45 from huggingface/Michelle-endpoint-updates

Update autoscaling.mdx

docs/source/autoscaling.mdx

@@ -10,7 +10,7 @@ The autoscaling process is triggered based on the accelerator's utilization metr
 
 - **GPU Accelerators**: A new replica is added when the average GPU utilization of all replicas over a 2-minute window reaches 80%.
 
-It's important to note that the scaling up process takes place every 3 minutes, while the scaling down process takes 5 minutes. This frequency ensures a balance between responsiveness and stability of the autoscaling system.
+It's important to note that the scaling up process takes place every minute, while the scaling down process takes 2 minutes. This frequency ensures a balance between responsiveness and stability of the autoscaling system, with a stabilization of 300 seconds once scaled up or down. 
 
 ## Considerations for Effective Autoscaling