AMD is quietly building a frame generation mode that beats Nvidia at its own game

AMD's latest Radeon drivers hide a Multi-Frame Generation mode that goes up to 8x, going one better than NVIDIA's 6x. Here's ...

A tiny London startup built a CUDA compiler that reportedly beats AMD's own tools on AMD hardware

Spectral Compute was founded in 2018 by four engineers with about 60 years of combined HPC optimization experience. The ...
PCMag Australia

AMD Ryzen AI Halo First Look: Giant Local AI Power in a Pint-Sized Box

I’ve received one of AMD’s first official AI developer boxes for testing, and it’s an impressive piece of AI hardware with a ...
Seeking Alpha

Why AMD's AI Position Is Expanding

AMD now expects AI server CPU demand to double, raising its 2030 server CPU TAM above $120 billion. Data Center revenue surged 57% to $5.8 billion as EPYC adoption expanded across cloud, enterprise, ...
GitHub

Intel Arc Pro B70 LLM Inference Server — Ubuntu Server Edition

Ubuntu Server 24.04 LTS install. For the Windows installer, see arc-pro-b70-inference-setup-windows. Automated setup script for running LLM inference on Intel Arc Pro B70 GPUs with llama.cpp SYCL — ...
GitHub

RadeonFlow Kernels

[2025/11] Easily Build and Share ROCm Kernels with Hugging Face – Discover how to easily build and share RadeonFlow_Kernels using Hugging Face's kernel-builder. [2025/06] AMD Developer Cloud now ...