[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"branding":3,"analytics":7,"article-new-technique-slashes-ai-chat-memory-use-by-up-to-90-percent":10,"sections":40},{"siteName":4,"siteTagline":5,"publisherName":4,"contactEmail":6},"The Revision","Tech news, decoded.","editor@therevision.news",{"gaMeasurementId":8,"adsenseClientId":9},"G-ZW2MV82GYR","ca-pub-8533917693782264",{"article":11},{"id":12,"slug":13,"title":14,"dek":15,"body_md":16,"tags_json":17,"published_at":18,"created_at":19,"updated_at":20,"status":21,"review_note":22,"review_notes":23,"image_url":22,"persona_id":22,"persona_name":22,"section":30,"tags":31,"sources":35,"feedback":39,"feedback_at":22,"cost_usd":39,"total_tokens":39},9277,"new-technique-slashes-ai-chat-memory-use-by-up-to-90-percent","New Technique Slashes AI Chat Memory Use by Up to 90 Percent","A new compression method keeps AI models fast and accurate while storing only a fraction of the data needed to remember long conversations.","A new compression scheme lets AI models hang onto long conversations using a fraction of the memory they normally need.\n\nResearchers behind a paper called ResidualKV built a system that splits an AI model's key-value cache - the running memory it uses to track everything said so far - into two parts: a small set of important reference tokens and compressed \"residual\" codes for everything else. Instead of permanently deleting older tokens to save space, as many existing methods do, ResidualKV keeps a lightweight record of them and reconstructs the full detail only when the model's attention mechanism actually needs it. Tested across Llama, Qwen, LLaVA-OV, and Qwen3-VL models, the method held performance close to systems using the full, uncompressed cache while using just 13-16% of the storage and 30% of the attention computation on the LongBench benchmark. On multimodal tasks the savings were steeper still: 8-10% storage and 10% computation, plus decoding speedups of up to 1.5x with cache quantization and 3.4x without it. Code is posted on GitHub.\n\nLong-context inference is one of the biggest cost centers in running AI models - every extra token of conversation history eats memory and slows attention calculations, which is why many chat products quietly cap or summarize history behind the scenes. A method that keeps near-full accuracy while cutting storage by 85% or more could let products hold onto much longer histories without a matching jump in GPU memory and latency costs.\n\nThese are benchmark numbers, not results from a production chatbot under real traffic, so how much of that efficiency survives outside LongBench and similar test suites is still an open question.","[\"ai\",\"llm\",\"kv-cache\",\"inference\"]","2026-10-01T04:00:00.000Z","2026-10-02T06:37:29.643Z","2026-10-02T06:37:35.851Z","published",null,[24],{"id":25,"reviewer":26,"round":27,"reason":28,"status":29},"editor-r1","editor",1,"The closing claim that labs with the biggest context windows 'already have their own undisclosed cache tricks' is an unsupported, unattributed assertion not grounded in the source material — cut it or attribute it, and keep the skepticism to verifiable limitations like benchmark-vs-production gaps.","resolved","ai",[30,32,33,34],"llm","kv-cache","inference",[36],{"name":37,"url":38},"arXiv cs.AI","https:\u002F\u002Farxiv.org\u002Fabs\u002F2602.08005",0,{"sections":41},[42,45,49,53,58,63,67,72,77,81,86,91,96,101],{"name":43,"slug":30,"count":44,"latest_published_at":18},"AI",5671,{"name":46,"slug":47,"count":48,"latest_published_at":18},"Security","security",820,{"name":50,"slug":51,"count":52,"latest_published_at":18},"Policy","policy",430,{"name":54,"slug":55,"count":56,"latest_published_at":57},"Deals","deals",298,"2026-09-30T21:00:26.000Z",{"name":59,"slug":60,"count":61,"latest_published_at":62},"Hardware","hardware",196,"2026-09-30T13:00:00.000Z",{"name":64,"slug":65,"count":66,"latest_published_at":18},"Science","science",165,{"name":68,"slug":69,"count":70,"latest_published_at":71},"Consumer Tech","consumer-tech",149,"2026-09-30T22:57:11.000Z",{"name":73,"slug":74,"count":75,"latest_published_at":76},"Dev Tools","dev-tools",93,"2026-10-01T02:30:48.000Z",{"name":78,"slug":79,"count":75,"latest_published_at":80},"Software","software","2026-09-30T21:41:11.000Z",{"name":82,"slug":83,"count":84,"latest_published_at":85},"Startups","startups",84,"2026-09-30T20:39:09.000Z",{"name":87,"slug":88,"count":89,"latest_published_at":90},"Gaming","gaming",51,"2026-09-30T16:24:30.000Z",{"name":92,"slug":93,"count":94,"latest_published_at":95},"General","general",50,"2026-09-30T21:37:54.000Z",{"name":97,"slug":98,"count":99,"latest_published_at":100},"Reviews","reviews",31,"2026-09-28T14:31:34.000Z",{"name":102,"slug":103,"count":104,"latest_published_at":105},"How-To","how-to",6,"2026-06-16T09:00:00.000Z"]