{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:N6LFWP3GV5K4KTTDWZ266EQXJZ","short_pith_number":"pith:N6LFWP3G","schema_version":"1.0","canonical_sha256":"6f965b3f66af55c54e63b675ef12174e7aa45970d4b06b1426de9823980e78ca","source":{"kind":"arxiv","id":"2606.30391","version":1},"attestation_state":"computed","paper":{"title":"Energy-Aware Scheduling for Serverless LLM Serving on Shared GPUs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DC","authors_text":"Aditya Dhakal, Dejan Milojicic, Gourav Rattihalli, Longfei Shangguan, Tianyu Wang","submitted_at":"2026-06-29T14:44:24Z","abstract_excerpt":"As LLM inference becomes a major cloud workload, its growing energy footprint makes cluster-wide energy optimization increasingly important. Serverless LLM serving helps platforms absorb traffic volatility by elastically sharing GPU resources across models, but this sharing also makes energy optimization difficult. Multiple co-resident models run under one device-wide operating point, while their resource demands and latency slack change across execution phases and load conditions. As a result, minimizing energy requires coordinated scheduling across request placement, runtime resource adaptat"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2606.30391","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2026-06-29T14:44:24Z","cross_cats_sorted":[],"title_canon_sha256":"067989e593b82bde112658d01954fc1b08ebb3c06f413bc256cc30a517c85fe9","abstract_canon_sha256":"9d3ec5e76aaaf777cd105ec0f998311c6520d179e482d6b6250458d33f6685e6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T02:18:13.321756Z","signature_b64":"lXhYBoDT36hEEYHU+E0+mcxequHw+ZogIjph/dd/oYTTEi7ERgpRpGG4S7l1Vs0Wxv2SsdFIrDHDRUAmKoT2DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6f965b3f66af55c54e63b675ef12174e7aa45970d4b06b1426de9823980e78ca","last_reissued_at":"2026-06-30T02:18:13.321244Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T02:18:13.321244Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Energy-Aware Scheduling for Serverless LLM Serving on Shared GPUs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DC","authors_text":"Aditya Dhakal, Dejan Milojicic, Gourav Rattihalli, Longfei Shangguan, Tianyu Wang","submitted_at":"2026-06-29T14:44:24Z","abstract_excerpt":"As LLM inference becomes a major cloud workload, its growing energy footprint makes cluster-wide energy optimization increasingly important. Serverless LLM serving helps platforms absorb traffic volatility by elastically sharing GPU resources across models, but this sharing also makes energy optimization difficult. Multiple co-resident models run under one device-wide operating point, while their resource demands and latency slack change across execution phases and load conditions. As a result, minimizing energy requires coordinated scheduling across request placement, runtime resource adaptat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.30391","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2606.30391/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.30391","created_at":"2026-06-30T02:18:13.321303+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.30391v1","created_at":"2026-06-30T02:18:13.321303+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.30391","created_at":"2026-06-30T02:18:13.321303+00:00"},{"alias_kind":"pith_short_12","alias_value":"N6LFWP3GV5K4","created_at":"2026-06-30T02:18:13.321303+00:00"},{"alias_kind":"pith_short_16","alias_value":"N6LFWP3GV5K4KTTD","created_at":"2026-06-30T02:18:13.321303+00:00"},{"alias_kind":"pith_short_8","alias_value":"N6LFWP3G","created_at":"2026-06-30T02:18:13.321303+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/N6LFWP3GV5K4KTTDWZ266EQXJZ","json":"https://pith.science/pith/N6LFWP3GV5K4KTTDWZ266EQXJZ.json","graph_json":"https://pith.science/api/pith-number/N6LFWP3GV5K4KTTDWZ266EQXJZ/graph.json","events_json":"https://pith.science/api/pith-number/N6LFWP3GV5K4KTTDWZ266EQXJZ/events.json","paper":"https://pith.science/paper/N6LFWP3G"},"agent_actions":{"view_html":"https://pith.science/pith/N6LFWP3GV5K4KTTDWZ266EQXJZ","download_json":"https://pith.science/pith/N6LFWP3GV5K4KTTDWZ266EQXJZ.json","view_paper":"https://pith.science/paper/N6LFWP3G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.30391&json=true","fetch_graph":"https://pith.science/api/pith-number/N6LFWP3GV5K4KTTDWZ266EQXJZ/graph.json","fetch_events":"https://pith.science/api/pith-number/N6LFWP3GV5K4KTTDWZ266EQXJZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N6LFWP3GV5K4KTTDWZ266EQXJZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N6LFWP3GV5K4KTTDWZ266EQXJZ/action/storage_attestation","attest_author":"https://pith.science/pith/N6LFWP3GV5K4KTTDWZ266EQXJZ/action/author_attestation","sign_citation":"https://pith.science/pith/N6LFWP3GV5K4KTTDWZ266EQXJZ/action/citation_signature","submit_replication":"https://pith.science/pith/N6LFWP3GV5K4KTTDWZ266EQXJZ/action/replication_record"}},"created_at":"2026-06-30T02:18:13.321303+00:00","updated_at":"2026-06-30T02:18:13.321303+00:00"}