{"type": "article", "title": "Why LLM decode is memory-bound, not compute-bound", "publisher": "Web Pulse", "url": "https://wpnews.pro/news/why-llm-decode-is-memory-bound-not-compute-bound", "original_source": "https://github.com/harshuljain13/llm-inference-at-scale/blob/master/content/00_foundations/00.1_why_llm_inference_is_different/why_llm_inference_is_different.md", "published": "2026-05-28T11:53:06+00:00", "accessed": "2026-07-12", "id": "why-llm-decode-is-memory-bound-not-compute-bound"}