{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:H76735DQCW5EPYAM56KUAXAKG3","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"412289bf5767ed313deab54834fb01a929d87b1ff501dffeae114fef5b478cbe","cross_cats_sorted":["cs.DC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MM","submitted_at":"2025-03-11T14:10:58Z","title_canon_sha256":"4389fbb177d79e840c2eb87f26b7f5b3a9d398ad2312897b0e113cf43132d654"},"schema_version":"1.0","source":{"id":"2503.08461","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.08461","created_at":"2026-07-05T10:28:59Z"},{"alias_kind":"arxiv_version","alias_value":"2503.08461v1","created_at":"2026-07-05T10:28:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.08461","created_at":"2026-07-05T10:28:59Z"},{"alias_kind":"pith_short_12","alias_value":"H76735DQCW5E","created_at":"2026-07-05T10:28:59Z"},{"alias_kind":"pith_short_16","alias_value":"H76735DQCW5EPYAM","created_at":"2026-07-05T10:28:59Z"},{"alias_kind":"pith_short_8","alias_value":"H76735DQ","created_at":"2026-07-05T10:28:59Z"}],"graph_snapshots":[{"event_id":"sha256:472e816a37cc3bd23daad1fad6133284135d7900a84c0fc4ee390db58eb13dfb","target":"graph","created_at":"2026-07-05T10:28:59Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2503.08461/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-modal Large Language Models (MLLMs) serving systems commonly employ KV-cache compression to reduce memory footprint. However, existing compression methods introduce significant processing overhead and queuing delays, particularly in concurrent serving scenarios. We present \\texttt{FastCache}, a novel serving framework that effectively addresses these challenges through two key innovations: (1) a dynamic batching strategy that optimizes request scheduling across prefill, compression, and decode stages, and (2) an efficient KV-cache memory pool mechanism that eliminates memory fragmentatio","authors_text":"Biao Hou, Hang Wu, Haojie Wang, Jianian Zhu, Jidong Zhai, Ruixuan Li, Yinghui Li","cross_cats":["cs.DC"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MM","submitted_at":"2025-03-11T14:10:58Z","title":"FastCache: Optimizing Multimodal LLM Serving through Lightweight KV-Cache Compression Framework"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.08461","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:45214727c42b8e78347ca8daa54ba272d1c6bbc815183237f4c785ecf994255e","target":"record","created_at":"2026-07-05T10:28:59Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"412289bf5767ed313deab54834fb01a929d87b1ff501dffeae114fef5b478cbe","cross_cats_sorted":["cs.DC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MM","submitted_at":"2025-03-11T14:10:58Z","title_canon_sha256":"4389fbb177d79e840c2eb87f26b7f5b3a9d398ad2312897b0e113cf43132d654"},"schema_version":"1.0","source":{"id":"2503.08461","kind":"arxiv","version":1}},"canonical_sha256":"3ffdfdf47015ba47e00cef95405c0a36fce05dc422ee74a8e323afc061866c09","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3ffdfdf47015ba47e00cef95405c0a36fce05dc422ee74a8e323afc061866c09","first_computed_at":"2026-07-05T10:28:59.920502Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:28:59.920502Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Rj3rPMYTVNhm1vxKHf1/OzNBTN1C7Zi7yQsj4idRMICxBOnC2cv64dTKUeuZJwWInJOH8bnssGUORRGLr6C6DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:28:59.920959Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.08461","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:45214727c42b8e78347ca8daa54ba272d1c6bbc815183237f4c785ecf994255e","sha256:472e816a37cc3bd23daad1fad6133284135d7900a84c0fc4ee390db58eb13dfb"],"state_sha256":"5edab9c98d228cef34e5692a1810f7fdf20a38055629b2efa98662a6d80332fc"}