{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:VHHD5NGW66Q4EWTND5RFUML5H5","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":"639b55ad7cf2dd979fb1cdefc16ba87540d07234d0dfd4b7f5b19beaa49d9fb4","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2025-12-10T09:47:40Z","title_canon_sha256":"cebcc4b2a0041fc529b1603a048ba154dab91f02d181e5141f076f1e07808df0"},"schema_version":"1.0","source":{"id":"2512.09472","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2512.09472","created_at":"2026-05-22T01:03:52Z"},{"alias_kind":"arxiv_version","alias_value":"2512.09472v2","created_at":"2026-05-22T01:03:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.09472","created_at":"2026-05-22T01:03:52Z"},{"alias_kind":"pith_short_12","alias_value":"VHHD5NGW66Q4","created_at":"2026-05-22T01:03:52Z"},{"alias_kind":"pith_short_16","alias_value":"VHHD5NGW66Q4EWTN","created_at":"2026-05-22T01:03:52Z"},{"alias_kind":"pith_short_8","alias_value":"VHHD5NGW","created_at":"2026-05-22T01:03:52Z"}],"graph_snapshots":[{"event_id":"sha256:11d90e2b2146807ca6d5da32fff9253221f56ea4fa3f93e43e223653132ebc6d","target":"graph","created_at":"2026-05-22T01:03:52Z","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/2512.09472/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deploying multiple models within shared GPU clusters is a key strategy to improve resource efficiency in large language model (LLM) serving. Existing multi-LLM serving systems improve GPU utilization at the cost of degraded inference performance, particularly time-to-first-token (TTFT). We attribute this degradation to the lack of awareness regarding future workload characteristics. In contrast, recent analyses have shown the strong periodicity and long-term predictability of real-world LLM serving workloads. In this paper, we propose one-for-many GPU prewarming, which proactively loads parame","authors_text":"Chen Sun, Chiheng Lou, Pengcheng Wang, Rui Kang, Sheng Qi, Xin Jin, Xuanzhe Liu, Yong Zhang","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2025-12-10T09:47:40Z","title":"WarmServe: Enabling One-for-Many GPU Prewarming for Multi-LLM Serving"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.09472","kind":"arxiv","version":2},"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":"sha256:1bf20e18c428da0af3c47f9ee97844fc69204b4a6bdb0664f935feba8b762d09","target":"record","created_at":"2026-05-22T01:03:52Z","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":"639b55ad7cf2dd979fb1cdefc16ba87540d07234d0dfd4b7f5b19beaa49d9fb4","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2025-12-10T09:47:40Z","title_canon_sha256":"cebcc4b2a0041fc529b1603a048ba154dab91f02d181e5141f076f1e07808df0"},"schema_version":"1.0","source":{"id":"2512.09472","kind":"arxiv","version":2}},"canonical_sha256":"a9ce3eb4d6f7a1c25a6d1f625a317d3f7f43a8e7cba97ecdd45c3fb1df40ca7b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a9ce3eb4d6f7a1c25a6d1f625a317d3f7f43a8e7cba97ecdd45c3fb1df40ca7b","first_computed_at":"2026-05-22T01:03:52.041121Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-22T01:03:52.041121Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Nff9zWA17jDDX/QYSIUSk4WEyFlufxFZ5a6SjcitBgoGMm7Hg4tv82xeBIGN5z+v0LgmEeuY6oL82OOYs8VMCA==","signature_status":"signed_v1","signed_at":"2026-05-22T01:03:52.041985Z","signed_message":"canonical_sha256_bytes"},"source_id":"2512.09472","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1bf20e18c428da0af3c47f9ee97844fc69204b4a6bdb0664f935feba8b762d09","sha256:11d90e2b2146807ca6d5da32fff9253221f56ea4fa3f93e43e223653132ebc6d"],"state_sha256":"77d25bdca6ce4c6289d4461a7ae47574f5a7f62000cbb1e8b1346cd3c19c1f25"}