The AMD Ryzen AI Halo is a mini-PC featuring the Zen 5 AMD Ryzen AI Max+ 395 processor with 16 cores and 32 threads. It includes 128 GB of unified memory, a removable 2 TB M.2 SSD, and utilizes AMD Radeon 8060S integrated graphics along with a neural processing unit (NPU) for AI development.

Performance per dollar for AI inference is improving, with GLM5.2 served on AMD MI355X achieving 2626 tokens per second per node and 213 tokens per second in a single stream at over 2x lower cost than Blackwell. Demand for inference is increasing rapidly, outpacing supply, as new frontier models are released frequently.

AMD is addressing customer inquiries regarding Linux support for the basic free version of Vivado. Users are seeking the reintroduction of this support for better compatibility with their systems.

AMD's Local, Open-Source AI Can Now Easily Interact With Your Gmail AMD software engineers continue rapidly advancing their open-source software efforts around local AI/LLM use on consumer-class Radeon and Ryzen hardware. AMD GAIA 0.17.6 was released on Thursday with more improvements for local AI processing on Windows, Linux, and even macOS. For those trusting enough in local LLM pipelines to do ...

GAIA SDK allows developers to build local AI agents using Python and C++ specifically optimized for AMD hardware. It provides tools and documentation for creating efficient AI applications.

AMD's ROCm software stack aims to compete with Nvidia's CUDA for data center GPU market share. Success in this endeavor is viewed as a significant challenge due to CUDA's established dominance.

AMD's GAIA Now Allows Building Custom AI Agents Via Chat, Becomes "True Desktop App" In addition to their efforts around the Lemonade SDK itself, AMD software engineers working on their AI initiatives continue to be investing quite a bit into the Lemonade-using GAIA, the project that originally stood for "Generative AI Is Awesome". AMD's GAIA now allows building your own custom AI agents via chatt...

AMD has developed the AMDXDNA accelerator driver for the mainline Linux kernel to support AMD Ryzen AI NPUs. User-space software for effectively utilizing these NPUs on Linux has been limited, with most applications relying on iGPU support instead.

Anush Elangovan, AMD's VP of AI Software, is developing a pure-Python AMD GPU user-space driver using Claude Code. This driver aims to support the testing and debugging of the ROCm/HIP user-space stack.

A small-scale distributed inference cluster can be built using AMD’s Ryzen™ AI Max+ AI PC platform to run a one trillion-parameter Large Language Model. A four-node cluster of Framework Desktop systems demonstrates the local inference of the Kimi K2.5 open-source model.