Volume 341, Issue 2 · 13 articles from 4 issues
AMD's Zen 6 Venice-X processor arrives in 2027 with 1152 MB of 3D V-Cache, 96 cores and a 5.15 GHz boost clock. Read more
ROCm 7.14 ships TheRock build system in production and adds support for Ryzen AI MAX PRO processors and PyTorch 2.12. Read more
AMD demonstrates building an agentic RAG research analyst on AMD GPUs using the hipVS vector search library. Read more
AMD shows how an AI code-assist tool can turn GPU profiler output into concrete kernel optimizations. Read more
AMD unveils full-stack agentic AI compute at Advancing AI 2026, led by Helios rack-scale, EPYC, and MI400. Read more
AMD extends its Inference Microservices and Solution Blueprints to run across multiple accelerator types. Read more
AMD engineers explain why a faster FP8 KV cache kernel failed to improve end-to-end LLM serving throughput on MI308X. Read more
AMD launches Venice, a server CPU portfolio with up to 256 cores, 1.6TB/s memory bandwidth and industry-first PCIe Gen 6. Read more
AMD acquires Toronto-based AI inference silicon startup Taalas to strengthen its inference roadmap. Read more
AMD, Supermicro, and Spectro Cloud launch AMD Instinct Coder, a turnkey local-first platform for enterprise AI coding. Read more
Whitepaper on rack-scale Supermicro and AMD Instinct infrastructure for production AI inference. Read more
AMD discusses agentic coding tools with Claude Code's creator and how they reshape engineering teams. Read more
AMD publishes a guide to running Meta's Apache 2.0 Muse Glimmer 30B model locally on AMD hardware. Read more