https://www.youtube.com/watch?v=kWSIFh8ICaA
Now at a time when memory and storage prices are at an all time high - they pull a move that directly hurts the customer.
1,123 karma · joined October 1, 2019
https://www.youtube.com/watch?v=kWSIFh8ICaA
Now at a time when memory and storage prices are at an all time high - they pull a move that directly hurts the customer.
and smolvm does clean up ephemeral runs if the machine run exits gracefully. I'll take a deeper look into this edge case and fix it today.
Fargate does not use firecracker. It was used for some internal workloads but was being migrated off at the end of 2025.
That way it can be elastic in CPU, memory and somewhat disk.
How far are you on your take?
will have a hosted platform soon with GPU support (vulkan)
CUDA support is possible based on a cursory dive. I'll keep you posted on it
ref: https://thevirtualhorizon.com/2024/05/31/how-to-configure-th...
And in the right situations, it can be enough.
It's a full vm
Because the videos are generated and pre-recorded on the website first?
Context: not well versed in machine learning
it's a lightweight vm because i see sandboxing as a feature of vm's.
Here's my 2cents: improve cold starts also means utilizing resources more effectively.
From cloud providers to end users - every ms both adds up and translates to additional waste of electricity/hardware and costs.
i bought the dang thing, let me decide how I use it.
it's all a political performance.
Remember when they made the decision for return to office and just...decided to post no support data on why they need to do it?
Today, I get ai support which fails to resolve my problem until a human steps in.
ai support is the new elevator music