AMD launched the Instinct MI400 Series GPUs for AI workloads, including the MI455X for frontier AI and the MI430X for sovereign AI and HPC. Built on CDNA 5 architecture and a 2nm process, the MI455X f…
AMD will host its Advancing AI 2026 summit on July 22-23 in San Francisco to showcase its MI350 series GPUs, which feature 288 GB of HBM3e memory versus Nvidia's 180 GB, as the chipmaker challenges Nv…
AMD introduced SGLang-ATOM, a bridge connecting the SGLang serving framework with ATOM's ROCm-native execution path to accelerate large language model inference on AMD Instinct GPUs. The integration u…
Open-weight model GLM-5.2 matched Claude Opus at a fraction of the cost, global LLM token spending fell 20% from its May peak, and a GPT-5.5 Codex flaw caused quiet output degradation, signaling a mar…
Wafer served GLM5.2 on AMD MI355X GPUs at 2626 tokens per second per node with over 2x lower cost than NVIDIA Blackwell, achieving 213 tok/s single stream. The company used MXFP4 quantization via AMD …
The GPU Compute Tightness Index fell to 43.8/100 as of June 29, 2026, entering Loose territory after a monthly drop of 13.7 points, indicating abundant idle AI infrastructure and supply exceeding near…
AMD introduces DP Attention and Two-Batch Overlap (TBO) optimizations for DeepSeek-V4 inference on MI355X GPUs, using a coordinated prefill scheduler called PrefillDelayer to reduce padding waste and …
The AI boom is pulling GPU vendors away from double-precision (FP64) hardware essential for scientific HPC, as NVIDIA, AMD, and Intel prioritize low-precision AI cores. New chips like NVIDIA's B200 an…
AMD and Rackspace Technology signed a definitive agreement for a phased 30 MW deployment of AMD-based AI compute across Rackspace's global data centers, starting late 2026 through 2028. The deal posit…
AMD and Rackspace Technology signed a definitive agreement to deploy an initial 30 MW of AMD AI compute across Rackspace data centers from late 2026 through 2028, integrating AMD Instinct GPUs and EPY…
Maincode, an Australian AI company, built a custom inference engine in Rust for the AMD MI355X GPU that bypasses the ROCm runtime entirely, achieving lower overhead on critical operations like tensor-…
DeepSeek v4, an open-source model from a Chinese lab, achieved a 100x performance improvement on AMD hardware within 26 days of its Day 0 release, driven by the AMD SGLang engineering team. The Infere…