LLM inference concepts explained in plain language, with playgrounds and diagrams.https://learnings.basani.me/https://learnings.basani.me/concepts/why-decoding-is-memory-bound/https://learnings.basani.me/concepts/why-decoding-is-memory-bound/To write each new token, the GPU has to read every weight of the model. That read, not the math, sets the speed limit.Tue, 20 Oct 2026 00:00:00 GMThttps://learnings.basani.me/log/2026-10-20-starting-the-site/https://learnings.basani.me/log/2026-10-20-starting-the-site/Tue, 20 Oct 2026 00:00:00 GMT