[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"topic-en-turboquant-makes-long-context-ai-much-cheaper":3},{"cluster":4,"timeline":17},{"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":16},"cc1bbc9d-156b-47b1-8c38-554dfca04095","turboquant-makes-long-context-ai-much-cheaper","TurboQuant makes long-context AI much cheaper",false,"active","4 ways TurboQuant’s 100x KV cache cut could lower long-context AI costs, ease GPU needs, and change model serving.","industry","en","2026-06-12T14:02:28.507608+00:00",null,2,"2026-06-13T00:40:00.030575+00:00",[18,25],{"id":19,"slug":20,"title":21,"summary":22,"category":11,"image_url":23,"cover_image":23,"published_at":24,"is_canonical_seed":8},"093f7c46-be7c-4b62-be00-73808a61e0a0","turboquant-amd-gpus-kv-cache-latency-en","TurboQuant on AMD GPUs cuts KV-cache latency","TurboQuant on AMD GPUs improves long-context LLM serving with up to 3.6x speedup and far lower KV-cache pressure.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1781299067778-3pzd.png","2026-06-12T21:17:26.063+00:00",{"id":26,"slug":27,"title":7,"summary":10,"category":11,"image_url":28,"cover_image":28,"published_at":29,"is_canonical_seed":30},"0ac121b9-de23-42b9-94f7-fac9ea703e18","turboquant-makes-long-context-ai-cheaper-en","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1781272983524-0j31.png","2026-06-12T14:02:27.632+00:00",true]