{"schemaVersion":1,"target":{"type":"reading","id":"385f2729e4d498898058de373d129cc808ffd572d34ad35e85de3e26ae193d35","revision":"dd2f0ac0-a8fe-4fff-86d9-38a232094827","revisionKind":"publication-id","title":"Zhikun Tao, Fangyong Jin and Junping Zhao test KV cache reuse across model updates","url":"https://escapemeridian.com/readings/zhikun-tao-fangyong-jin-and-junping-zhao-test-kv-cache-reuse-385f2729"},"source":{"type":"source","id":"https://arxiv.org/abs/2611.14051","revision":"f708721ef1daa3a0a1a8768949593b2d4fccea83f7bd5b2adc1520159056aa1d","revisionKind":"sha256-source-text","title":"Can KV Cache Be Reused Across Model Updates? A DeepSeek-V4-Flash Case Study","url":"https://arxiv.org/abs/2611.14051"},"status":"available","items":[],"next":null,"scope":"Explicit citations in public readings and public file attachments to this reading. Shared topics are not citations. Other artifact types need an explicit reference adapter."}