{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:LJSVDZREN5YL7ME3UL6MJLO67P","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":"5a8ff2ae7fb97bbeb32ed560825d62d058425765c2df7c2ca8344e17d545db03","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-25T05:24:53Z","title_canon_sha256":"3e27e0c577d27852ef193bb39dd95f797fb62dffc965eadf6a993ed0cf6053cb"},"schema_version":"1.0","source":{"id":"2411.16102","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.16102","created_at":"2026-06-09T01:04:37Z"},{"alias_kind":"arxiv_version","alias_value":"2411.16102v2","created_at":"2026-06-09T01:04:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.16102","created_at":"2026-06-09T01:04:37Z"},{"alias_kind":"pith_short_12","alias_value":"LJSVDZREN5YL","created_at":"2026-06-09T01:04:37Z"},{"alias_kind":"pith_short_16","alias_value":"LJSVDZREN5YL7ME3","created_at":"2026-06-09T01:04:37Z"},{"alias_kind":"pith_short_8","alias_value":"LJSVDZRE","created_at":"2026-06-09T01:04:37Z"}],"graph_snapshots":[{"event_id":"sha256:6ae3d9bd91484327d86be2cb7296c2409a0283fda04280fd1f7ed8d4d3a133c2","target":"graph","created_at":"2026-06-09T01:04:37Z","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/2411.16102/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Offline batch inference, which leverages the flexibility of request batching to achieve higher throughput and lower costs, is becoming more popular for latency-insensitive applications. Meanwhile, recent progress in model capability and modality makes requests more diverse in compute and memory demands, creating unique opportunities for throughput improvement by resource overlapping. However, a request schedule that maximizes resource overlapping can conflict with the schedule that maximizes prefix sharing, a widely-used performance optimization, causing sub-optimal inference throughput. We pr","authors_text":"Baris Kasikci, Ion Stoica, Jiarong Xing, Kan Zhu, Lianmin Zheng, Shuo Yang, Yang Zhou, Yilong Zhao","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-25T05:24:53Z","title":"BlendServe: Optimizing Offline Inference for Auto-regressive Large Models with Resource-aware Batching"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.16102","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:cd84aa673b7fc3a0125e5ac806a092a464f4ec19d8374e91997170ca8d200e28","target":"record","created_at":"2026-06-09T01:04:37Z","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":"5a8ff2ae7fb97bbeb32ed560825d62d058425765c2df7c2ca8344e17d545db03","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-25T05:24:53Z","title_canon_sha256":"3e27e0c577d27852ef193bb39dd95f797fb62dffc965eadf6a993ed0cf6053cb"},"schema_version":"1.0","source":{"id":"2411.16102","kind":"arxiv","version":2}},"canonical_sha256":"5a6551e6246f70bfb09ba2fcc4addefbe771ed9f1ac85c4494b79105e116a1fd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5a6551e6246f70bfb09ba2fcc4addefbe771ed9f1ac85c4494b79105e116a1fd","first_computed_at":"2026-06-09T01:04:37.647628Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-09T01:04:37.647628Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"89fDLYVGfsaHoFX5UkiJqeSfjoZQeI8PiaIZtzFN7HCIzdA6j6BErovDGTRsKB5zs+I9/qeGDcRa41pNx0NBBQ==","signature_status":"signed_v1","signed_at":"2026-06-09T01:04:37.648148Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.16102","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cd84aa673b7fc3a0125e5ac806a092a464f4ec19d8374e91997170ca8d200e28","sha256:6ae3d9bd91484327d86be2cb7296c2409a0283fda04280fd1f7ed8d4d3a133c2"],"state_sha256":"71d61755ce7047e2b75383896f6658d2a07351795314b9b9be9194b6fc877d7f"}