Curated developer articles, tutorials, and guides — auto-updated hourly


A 31% latency reduction is within reach if you adjust three AMD GPU kernel knobs. I walked through t...


Latency on AMD Developer Cloud spikes 40% more often than expected. By re‑architecting NVLink links ...


A student can run the next‑gen legal AI Qwen 3.5 on AMD’s cloud without spending a dime. Follow a si...


AMD’s ROCm cuts LLM inference latency by 85%, letting developers ship AI features faster and cheaper...


Cut Hermes Agent inference from 200 ms to 100 ms on AMD Developer Cloud without spending a dime. Fol...