{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:OSEMS3TZORLVJLMGUZRHSCNFI2","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":"b0ac48d841165a30158effd629097aa7befbb1cce0b24754c4d8b1287306514f","cross_cats_sorted":["cs.AI","cs.DC","math.OC","stat.ML"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-15T16:00:21Z","title_canon_sha256":"d9595304d1dda16053f3ee96a4ab3a401fc28fc848c753d9819b5d0626132ef1"},"schema_version":"1.0","source":{"id":"2504.11320","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.11320","created_at":"2026-05-20T00:00:19Z"},{"alias_kind":"arxiv_version","alias_value":"2504.11320v3","created_at":"2026-05-20T00:00:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.11320","created_at":"2026-05-20T00:00:19Z"},{"alias_kind":"pith_short_12","alias_value":"OSEMS3TZORLV","created_at":"2026-05-20T00:00:19Z"},{"alias_kind":"pith_short_16","alias_value":"OSEMS3TZORLVJLMG","created_at":"2026-05-20T00:00:19Z"},{"alias_kind":"pith_short_8","alias_value":"OSEMS3TZ","created_at":"2026-05-20T00:00:19Z"}],"graph_snapshots":[{"event_id":"sha256:c4ee5b97c4a50193d4b4fcd7b05110808165f954a86248c88b2cc519033cf347","target":"graph","created_at":"2026-05-20T00:00:19Z","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/2504.11320/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models now serve millions of users daily, with providers incurring costs exceeding $700,000 per day. Each request requires token-by-token inference, making GPU scheduling central to latency, capacity, and cost. The difficulty is endogenous memory growth: generated tokens expand the Key-Value (KV) cache, and overflow can evict in-progress requests and waste prior computation. We formulate inference as a multi-stage online scheduling problem with endogenous memory growth, linear iteration times, and GPU-resident KV-cache constraints. We introduce a fluid model that characterizes e","authors_text":"David Simchi-Levi, Gan Luo, Ruicheng Ao, Xinshang Wang","cross_cats":["cs.AI","cs.DC","math.OC","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-15T16:00:21Z","title":"Optimizing LLM Inference: Fluid-Guided Online Scheduling with Memory Constraints"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.11320","kind":"arxiv","version":3},"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:ce2ad84d76db07add863148ba62878f2fe293dd05e5d4a916e56987dea8bf713","target":"record","created_at":"2026-05-20T00:00:19Z","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":"b0ac48d841165a30158effd629097aa7befbb1cce0b24754c4d8b1287306514f","cross_cats_sorted":["cs.AI","cs.DC","math.OC","stat.ML"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-15T16:00:21Z","title_canon_sha256":"d9595304d1dda16053f3ee96a4ab3a401fc28fc848c753d9819b5d0626132ef1"},"schema_version":"1.0","source":{"id":"2504.11320","kind":"arxiv","version":3}},"canonical_sha256":"7488c96e79745754ad86a6627909a54683e1c9492d29204fd8335593f731fcab","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7488c96e79745754ad86a6627909a54683e1c9492d29204fd8335593f731fcab","first_computed_at":"2026-05-20T00:00:19.287871Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:00:19.287871Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oPlEMD8keRnLB0Os7aoMhR7GNmtlRXVMY2vMctyoVtq1w2tqm1qjvV6sq8NVsQx7ZqGtH+ZgEhb8ZD7gk6lKCg==","signature_status":"signed_v1","signed_at":"2026-05-20T00:00:19.288648Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.11320","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ce2ad84d76db07add863148ba62878f2fe293dd05e5d4a916e56987dea8bf713","sha256:c4ee5b97c4a50193d4b4fcd7b05110808165f954a86248c88b2cc519033cf347"],"state_sha256":"42691c8bbdb549c6128a2f56b8ec520f515555df27991a6204affcf68f591388"}