[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"topic-en-llm-inference-hardware-needs-memory-not-more-flops":3},{"cluster":4,"timeline":16},{"id":5,"slug":6,"title":7,"pinned":8,"status":9,"summary":10,"category":11,"language":12,"created_at":13,"merged_into":14,"article_count":15,"first_seen_at":13,"last_updated_at":13},"f911f187-c66f-4e8f-818c-7f55c040fe5e","llm-inference-hardware-needs-memory-not-more-flops","LLM Inference Hardware Needs Memory, Not More FLOPs",false,"active","This paper argues that LLM inference is bottlenecked by memory and interconnect, not raw compute.","research","en","2026-07-21T08:32:28.903231+00:00",null,1,[17],{"id":18,"slug":19,"title":7,"summary":10,"category":11,"image_url":20,"cover_image":20,"published_at":21,"is_canonical_seed":22},"d29a94bf-a060-4890-b2d7-46707ee356d5","llm-inference-hardware-memory-interconnect-en","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1784622785298-e9gf.png","2026-07-21T08:32:27.973+00:00",true]