We look at AI the way our customers do, which is why we built the Puget Systems Docker App Packs: to help you get up and running with AI inference fast!


We look at AI the way our customers do, which is why we built the Puget Systems Docker App Packs: to help you get up and running with AI inference fast!

The performance improvement with the new Zen4 TrPRO over the Zen3 TrPRO is very impressive!
My first recommendation for a Scientific and Engineering workstation CPU would now be the AMD Zen4 architecture as either Zen4 Threadripper PRO or Zen4 EPYC for multi-socket systems.

This post is Part 2 in a series on how to configure a system for LLM deployments and development usage. Part 2 is about installing and configuring container tools, Docker and NVIDIA Enroot.

This post is Part 1 in a series on how to configure a system for LLM deployments and development usage. The configuration will be suitable for multi-user deployments and also useful for smaller development systems. Part 1 is about the base Linux server setup.

This is a short note on setting up the Apache web server to allow system users to create personal websites and web apps in their home directories.

This post is a short HowTo on passing Linux kernel boot options during OS installation and persisting them for future system starts

Learning go (Golang) is one of my resolutions for 2023. It looks like a great cross platform compiled language with a straightforward simple syntax with modern features. I have multi-OS projects in mind where I expect it to be ideal. So, I’ll get started …
This post is a follow up to How-To: Make Ubuntu Autoinstall ISO with Cloud-init written in Sept. 2021. We will look at changes needed for Ubuntu 22.04.
This post presents preliminary ML-AI and Scientific application performance results comparing NVIDIA RTX 4090 and RTX 3090 GPUs. These are early results using the NVIDIA CUDA 11.8 driver.
This post presents scientific application performance testing on the new AMD Ryzen 7950X. I am impressed! Seven applications that are heavy parallel numerical compute workloads were tested. The 7950X outperformed the Ryzen 5950X by as much as 25-40%. For some of the applications it provided nearly 50% of the performance of the much larger and more expensive Threadripper Pro 5995WX 64-core processor. That’s remarkable for a $700 CPU! The Ryzen 7950X is not in the same platform class as the Tr Pro but it is a respectable, budget friendly, numerical computing processor.