Changelog #60 - Serverless RTX GPUs in technical preview, Autoscaling: Scale based on concurrent requests, and more

Hello, and welcome to this week’s changelog update! Let’s jump into what’s new:

  1. Serverless RTX GPUs in technical preview

    Serverless RTX GPUs are now available to all Starter and Startup organizations in technical preview. You can run LLMs, Computer Vision, and AI inference in seconds. Get access to our other GPUs by joining the private preview.

  2. Autoscaling: Scale based on concurrent requests

    Services can now scale up and down based on the number of concurrent requests per Instance. We monitor the number of open connections for each Instance every 15 seconds to compute the concurrent request number. This is available using the CLI.

  3. Show secret values in the control panel

    You can now display the value of a secret in the control panel. This is useful if you want to check the value of an existing secret and make sure it’s properly set. Previously, this option was only available using the CLI.

  4. New tutorial: Deploy Infisical on Koyeb

    Learn how to deploy Infisical on Koyeb. Infisical is an open-source secret management platform to securely store and manage secrets for both users and applications. This is also a great opportunity to discover and use our serverless PostgreSQL databases.