{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:UUYS7JMNLVFHRZID3JFVYPQCMJ","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":"b1e29796045bb59d6683d3450e7c1867a2402c0e568c4dbde381c7f848f7b374","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.DC","submitted_at":"2024-12-17T02:44:43Z","title_canon_sha256":"edd63a946282b165647ac13059a47d103313dbb3ee9c4e65d1d891b671ca3424"},"schema_version":"1.0","source":{"id":"2412.12488","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.12488","created_at":"2026-07-05T09:50:15Z"},{"alias_kind":"arxiv_version","alias_value":"2412.12488v1","created_at":"2026-07-05T09:50:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.12488","created_at":"2026-07-05T09:50:15Z"},{"alias_kind":"pith_short_12","alias_value":"UUYS7JMNLVFH","created_at":"2026-07-05T09:50:15Z"},{"alias_kind":"pith_short_16","alias_value":"UUYS7JMNLVFHRZID","created_at":"2026-07-05T09:50:15Z"},{"alias_kind":"pith_short_8","alias_value":"UUYS7JMN","created_at":"2026-07-05T09:50:15Z"}],"graph_snapshots":[{"event_id":"sha256:502cf8a011ba3db81a4526474c13f24e5bfb8823d6646db8d2d20ee9fe335e5c","target":"graph","created_at":"2026-07-05T09:50:15Z","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/2412.12488/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The recent advances in LLMs bring a strong demand for efficient system support to improve overall serving efficiency. As LLM inference scales towards multiple GPUs and even multiple compute nodes, various coordination patterns, such as prefill-decode disaggregation and context migration, arise in serving systems. Most inference services today expose a coarse-grained request-level API with a pre-configured coordination strategy, limiting the ability to customize and dynamically reconfigure the coordination. In this paper, we propose LLM microserving, a multi-level architecture for structuring a","authors_text":"Charlie F. Ruan, Hongyi Jin, Ruihang Lai, Tianqi Chen, Todd C. Mowry, Xupeng Miao, Yingcheng Wang, Zhihao Jia","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.DC","submitted_at":"2024-12-17T02:44:43Z","title":"A System for Microserving of LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.12488","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:be351ec89137902e27c1dd5bf53ea74bad73c70d4c931c841a2ab087651732e8","target":"record","created_at":"2026-07-05T09:50:15Z","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":"b1e29796045bb59d6683d3450e7c1867a2402c0e568c4dbde381c7f848f7b374","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.DC","submitted_at":"2024-12-17T02:44:43Z","title_canon_sha256":"edd63a946282b165647ac13059a47d103313dbb3ee9c4e65d1d891b671ca3424"},"schema_version":"1.0","source":{"id":"2412.12488","kind":"arxiv","version":1}},"canonical_sha256":"a5312fa58d5d4a78e503da4b5c3e02625c40c8b00c6ea0ee4469a57fe6029c9f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a5312fa58d5d4a78e503da4b5c3e02625c40c8b00c6ea0ee4469a57fe6029c9f","first_computed_at":"2026-07-05T09:50:15.710800Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:50:15.710800Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AnPbsT+vqDeTUtEuqvVfO+F6fgJtm5ivilAPgkqGdnBzJrt/HPcMIqZnt3hwVH1qAhICFSIBQ0d97SIVpdDSDg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:50:15.711360Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.12488","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:be351ec89137902e27c1dd5bf53ea74bad73c70d4c931c841a2ab087651732e8","sha256:502cf8a011ba3db81a4526474c13f24e5bfb8823d6646db8d2d20ee9fe335e5c"],"state_sha256":"85a276ba0d3f250695458bd256314f32b29b731a7ed004aae57ae65a2537e171"}