AWS Auto Scaling VS Amazon Inferentia

AWS Auto-Scaling is a service that automatically adjusts the capacity of an application in response to changing demand. It monitors resource utilization and scales resources up or down as necessary. By using AWS Auto Scaling, businesses can ensure that their applications are always running at optimal performance levels, without wasting resources or energy. - Source: dev.to / about 1 year ago

Auto scaling lets you scale in/out your servers based on various conditions. So, you could choose to have a minimum capacity as default and let AWS scale it up automatically when needed. You could also schedule the scaling events based on time (For ex: scale to 2x servers during peak times and back to normal during normal hours) There are also other benefits that come with AWS like better eco-system of tools and... - Source: dev.to / over 1 year ago

Guys, whats this? Sounds kinda OP if you ask me Https://aws.amazon.com/autoscaling/. Source: about 2 years ago

AWS Auto Scaling – Makes sure that the application scales based on the number of concurrent requests. - Source: dev.to / over 2 years ago

Many customers start their cloud journey with a lift-and-shift approach, running their NTier .NET Framework applications on EC2 without any code changes. It’s common for these deployments to have more than one EC2 Windows instance with an Application Load Balancer (ALB), routing the user requests to one of the EC2 instances. A stateful application can have session affinity (sticky sessions) enabled at the ALB... - Source: dev.to / over 2 years ago

> Here it says they're going to use Amazon's chips for training and inference, but...Amazon doesn't have its own chips yet??? Amazon has had its own chips for years. https://aws.amazon.com/machine-learning/inferentia/ https://aws.amazon.com/machine-learning/trainium/. - Source: Hacker News / 28 days ago

No idea if it's any good or not, but Amazon has their own "Inferentia" chips. https://aws.amazon.com/machine-learning/inferentia/. - Source: Hacker News / 28 days ago

You can use them today on AWS. [0] https://aws.amazon.com/machine-learning/inferentia/. - Source: Hacker News / 11 months ago

Amazon has their own TPU equivalents for training and inference: https://aws.amazon.com/machine-learning/trainium/ https://aws.amazon.com/machine-learning/inferentia/ But, I really don't think this would be a limiting factor regardless. It's not as if an Amazon or Microsoft sized company is incapable of developing custom silicon to meet an objective, once an objective is identified. - Source: Hacker News / about 1 year ago

You are mistaken. See https://en.m.wikipedia.org/wiki/Annapurna_Labs and some of their work (specialized chips similar to Google’s TPU): https://aws.amazon.com/machine-learning/inferentia/. Source: over 1 year ago