Back Issues/Search Home → Archive → RSS → Subscribe → Services → Popular →

AMD — Archive · Vol 342 Issue 4

3 articles that week

AMD, Friday, September 25th, 2026

UltraQuant on AMD Instinct: More Efficient Agentic Serving for Qwen3.8-MXFP4

Vol 342 · Issue 4 · 2026-09-25

AMD's ROCm blog details UltraQuant, a native 4-bit MXFP4 KV cache that speeds up Qwen3.8 decoding on Instinct MI355X GPUs.

more →

AMD, Wednesday, September 23rd, 2026

Advanced Insights: How Zen Architecture Evolves for the Agentic AI Era

Vol 342 · Issue 4 · 2026-09-23

AMD's CTO and chief CPU architect discuss how Zen x86 architecture is evolving to meet agentic AI demands.

more →

AMD, Monday, September 21st, 2026

Hyperloom: A Multi-Agent Harness for Autonomous Inference Optimization on AMD GPUs

Vol 342 · Issue 4 · 2026-09-21

AMD's Hyperloom uses a multi-agent harness to autonomously optimize inference, achieving a median 1.73x throughput gain.

more →