{"schemaVersion":1,"target":{"type":"reading","id":"d39f994a61c8d156e1607ba4b462c25b7dc7b1560a569f01e1f476f9eb278b75","revision":"d2ff9e60-7812-4b61-8b75-737a9ff81972","revisionKind":"publication-id","title":"arXiv cs.AI: FlashOffloading: Low-Latency KV Cache Offloading for Long-Context LLM Serving","url":"https://escapemeridian.com/readings/arxiv-cs-ai-flashoffloading-low-latency-kv-cache-offloading-for-d39f994a"},"source":{"type":"source","id":"https://arxiv.org/abs/2611.07542","revision":"c5202b563ffa48fb40c585720c5334bdd0ec5051556e759f3392f307e8156ac9","revisionKind":"sha256-source-text","title":"FlashOffloading: Low-Latency KV Cache Offloading for Long-Context LLM Serving","url":"https://arxiv.org/abs/2611.07542"},"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."}