[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"branding":3,"analytics":7,"article-kernelsight-lm-predicts-llm-inference-latency-without-the-hardware":10,"sections":41},{"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":36,"feedback":40,"feedback_at":22,"cost_usd":40,"total_tokens":40},2599,"kernelsight-lm-predicts-llm-inference-latency-without-the-hardware","KernelSight-LM Predicts LLM Inference Latency Without the Hardware","A new simulator predicts LLM inference latency kernel by kernel, hitting 3.8% per-kernel error, though end-to-end TTFT can still miss by up to 15.4%.","A new inference simulator predicts LLM performance kernel by kernel, potentially replacing the slow, deployment-specific GPU benchmarks that keep ML engineers waiting.\n\nKernelSight-LM decomposes each inference step into three sub-models: a roofline kernel model with a learned efficiency term, a communication model, and a host-overhead model, coordinated by a discrete-event scheduler that also handles prefix caching and continuous batching. The tool ships in two tiers. The cross-generation tier relies only on hardware specifications and microbenchmarks from previously profiled GPUs, predicting per-kernel latency on an unseen GPU to 12.1% error, 1.8 times better than a plain roofline baseline. The target-measured tier adds a single microbenchmark sweep on the actual hardware, sharpening per-kernel error to 3.8%, a 7.3x improvement over a comparable baseline.\n\nThe 3.8% figure is per-kernel accuracy, not the metric practitioners actually stress-test against. End-to-end time-to-first-token (TTFT), the latency number that determines whether a deployment meets its SLA, carries errors of 15.4% in the cross-generation tier and 14.3% in the target-measured tier. Throughput predictions land around 3% error in both configurations, and time-per-output-token (TPOT) sits at 12.8% and 6.2% respectively, so the tool is more reliable for capacity planning than for tight latency commitments.\n\nThe paper covers six model families, which is encouraging, but whether a 15% TTFT miss fits your deployment budget depends entirely on what you are building.","[\"llm-inference\",\"gpu\",\"benchmarking\",\"machine-learning\"]","2026-06-30T04:00:00.000Z","2026-06-30T08:55:10.616Z","2026-06-30T08:55:13.330Z","published",null,[24],{"id":25,"reviewer":26,"round":27,"reason":28,"status":29},"editor-r1","editor",1,"The dek claims 'under 4% error' but the source specifies 3.8% per-kernel error; more critically, the body omits the end-to-end error figures (up to 15.4% TTFT in cross-generation tier) which are the numbers practitioners actually care about and which significantly qualify the headline accuracy claim — the draft should surface these and distinguish per-kernel error from end-to-end error.","resolved","ai",[32,33,34,35],"llm-inference","gpu","benchmarking","machine-learning",[37],{"name":38,"url":39},"arXiv cs.AI","https:\u002F\u002Farxiv.org\u002Fabs\u002F2606.28565",0,{"sections":42},[43,47,52,57,62,67,72,77,82,87,92,96,101,106],{"name":44,"slug":30,"count":45,"latest_published_at":46},"AI",2590,"2026-07-16T04:00:00.000Z",{"name":48,"slug":49,"count":50,"latest_published_at":51},"Security","security",294,"2026-07-15T19:59:48.000Z",{"name":53,"slug":54,"count":55,"latest_published_at":56},"Deals","deals",179,"2026-06-29T20:02:07.000Z",{"name":58,"slug":59,"count":60,"latest_published_at":61},"Policy","policy",158,"2026-07-16T00:02:48.000Z",{"name":63,"slug":64,"count":65,"latest_published_at":66},"Hardware","hardware",122,"2026-07-14T19:46:26.000Z",{"name":68,"slug":69,"count":70,"latest_published_at":71},"Consumer Tech","consumer-tech",93,"2026-07-13T13:20:48.000Z",{"name":73,"slug":74,"count":75,"latest_published_at":76},"Software","software",70,"2026-07-13T19:52:25.000Z",{"name":78,"slug":79,"count":80,"latest_published_at":81},"Science","science",66,"2026-07-10T10:29:37.000Z",{"name":83,"slug":84,"count":85,"latest_published_at":86},"Dev Tools","dev-tools",59,"2026-07-07T04:00:00.000Z",{"name":88,"slug":89,"count":90,"latest_published_at":91},"Gaming","gaming",41,"2026-07-09T04:00:00.000Z",{"name":93,"slug":94,"count":90,"latest_published_at":95},"Startups","startups","2026-06-29T20:55:50.000Z",{"name":97,"slug":98,"count":99,"latest_published_at":100},"General","general",29,"2026-07-10T22:28:58.000Z",{"name":102,"slug":103,"count":104,"latest_published_at":105},"Reviews","reviews",20,"2026-06-24T12:00:01.000Z",{"name":107,"slug":108,"count":109,"latest_published_at":110},"How-To","how-to",6,"2026-06-16T09:00:00.000Z"]