News in the Channel - issue #43

PRODUCT LAUNCHES AMD

High performance One of the products launched at the event was 6th Gen EPYC processors, which deliver the broadest server CPU portfolio for agentic AI, spanning cloud, enterprise, general-purpose and high- performance computing (HPC) workloads. With leadership per-core performance and the highest thread density, they enable the most agents per watt, per dollar and per rack. For AI host nodes, 6th Gen EPYC CPUs deliver the speed and memory bandwidth to keep accelerators fully fed. And for general-purpose servers, they bring leadership performance and energy efficiency to run business critical applications and AI support tasks. Allied to that was the launch of AMD Instinct™ MI400 Series GPUs, which enable AMD to deliver powerful performance for cloud, enterprise and HPC workloads. AMD Instinct MI455X GPUs deliver 34x higher token throughput compared to MI355X GPUs. For high-precision workloads, the AMD Instinct™ MI430X accelerator is the most advanced for HPC and sovereign AI with up to 288 TFLOPS of hardware-based FP64 performance for scientific computing. Instinct MI430X accelerators are powering the next wave of exascale-class supercomputers across the US and Europe. AMD also launched the Instinct MI350P GPU, bringing seamless AI acceleration to existing infrastructure with leadership token economics. MI350P GPUs deliver up to 4.2x more tokens per second per dollar than the competition. Supporting developers Another launch was the Ryzen AI Halo, which gives developers a local platform for building, testing and iterating on AI models, with 128GB of unified memory and support for models up to 200 billion parameters. AMD is also expanding its partnership with Hugging Face to bring optimised open models, libraries

AMD 6th Gen EPYC processors

and toolkits to Ryzen AI Halo, helping developers spend less time configuring infrastructure and more time building applications. Later this year, every AMD Ryzen AI Halo developer platform will ship with a free year of Hugging Face PRO. AMD is already pushing the capabilities of local AI further with the recently announced Ryzen™ AI Max PRO 400 Series processors, with an increased unified memory of 192GB and supporting models up to 300 billion parameters. Developer platforms featuring Ryzen AI Max PRO 400 will be available in the Ryzen AI Halo and OEM systems later this year. These systems will enable larger open models, longer context, deeper agent memory and more sophisticated multiagent workflows — all running locally on a personal system. This snapshot of some of the major launches from Advancing AI 2026 shows how AMD technologies are helping customers scale quickly and accelerate enterprise transformation and will be impacting businesses large and small around the world. n

Developer platforms featuring Ryzen AI Max PRO 400 will be available in the Ryzen AI Halo and OEM systems later this year. These systems will enable larger open

models, longer context, deeper

agent memory and more sophisticated

multiagent workflows...