{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:NCZUDUJYVSRNTG4CNSHPWCSZ75","short_pith_number":"pith:NCZUDUJY","schema_version":"1.0","canonical_sha256":"68b341d138aca2d99b826c8efb0a59ff617d0d1db1001a72d293518efa9750b1","source":{"kind":"arxiv","id":"2506.12598","version":1},"attestation_state":"computed","paper":{"title":"ECLIP: Energy-efficient and Practical Co-Location of ML Inference on Spatially Partitioned GPUs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SY"],"primary_cat":"eess.SY","authors_text":"Ali Jahanshahi, Daniel Wong, Hyoseung Kim, Ryan Quach, Yidi Wang","submitted_at":"2025-06-14T18:34:48Z","abstract_excerpt":"As AI inference becomes mainstream, research has begun to focus on improving the energy consumption of inference servers. Inference kernels commonly underutilize a GPU's compute resources and waste power from idling components. To improve utilization and energy efficiency, multiple models can co-locate and share the GPU. However, typical GPU spatial partitioning techniques often experience significant overheads when reconfiguring spatial partitions, which can waste additional energy through repartitioning overheads or non-optimal partition configurations. In this paper, we present ECLIP, a fra"},"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":"2506.12598","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.SY","submitted_at":"2025-06-14T18:34:48Z","cross_cats_sorted":["cs.SY"],"title_canon_sha256":"6cd367345480d77daa43fc194b9695c9c1c6b3e5959134565d096b5d09d834fa","abstract_canon_sha256":"0f8ba18a1a8ac703b2a235b0d9c93ccd21a89e9215f5ebe16c96bdf63e9766e8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:21:56.150028Z","signature_b64":"x+maG4SSQ9ICUOJKDLgdAEdUw26ZX0iZjVvvZbgNC3MmKEpdGSdl4OS1gB25ojF7sCgbBInxwsgbRmHHEP0kDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"68b341d138aca2d99b826c8efb0a59ff617d0d1db1001a72d293518efa9750b1","last_reissued_at":"2026-07-05T11:21:56.149536Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:21:56.149536Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ECLIP: Energy-efficient and Practical Co-Location of ML Inference on Spatially Partitioned GPUs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SY"],"primary_cat":"eess.SY","authors_text":"Ali Jahanshahi, Daniel Wong, Hyoseung Kim, Ryan Quach, Yidi Wang","submitted_at":"2025-06-14T18:34:48Z","abstract_excerpt":"As AI inference becomes mainstream, research has begun to focus on improving the energy consumption of inference servers. Inference kernels commonly underutilize a GPU's compute resources and waste power from idling components. To improve utilization and energy efficiency, multiple models can co-locate and share the GPU. However, typical GPU spatial partitioning techniques often experience significant overheads when reconfiguring spatial partitions, which can waste additional energy through repartitioning overheads or non-optimal partition configurations. In this paper, we present ECLIP, a fra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.12598","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/2506.12598/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":"2506.12598","created_at":"2026-07-05T11:21:56.149594+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.12598v1","created_at":"2026-07-05T11:21:56.149594+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.12598","created_at":"2026-07-05T11:21:56.149594+00:00"},{"alias_kind":"pith_short_12","alias_value":"NCZUDUJYVSRN","created_at":"2026-07-05T11:21:56.149594+00:00"},{"alias_kind":"pith_short_16","alias_value":"NCZUDUJYVSRNTG4C","created_at":"2026-07-05T11:21:56.149594+00:00"},{"alias_kind":"pith_short_8","alias_value":"NCZUDUJY","created_at":"2026-07-05T11:21:56.149594+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/NCZUDUJYVSRNTG4CNSHPWCSZ75","json":"https://pith.science/pith/NCZUDUJYVSRNTG4CNSHPWCSZ75.json","graph_json":"https://pith.science/api/pith-number/NCZUDUJYVSRNTG4CNSHPWCSZ75/graph.json","events_json":"https://pith.science/api/pith-number/NCZUDUJYVSRNTG4CNSHPWCSZ75/events.json","paper":"https://pith.science/paper/NCZUDUJY"},"agent_actions":{"view_html":"https://pith.science/pith/NCZUDUJYVSRNTG4CNSHPWCSZ75","download_json":"https://pith.science/pith/NCZUDUJYVSRNTG4CNSHPWCSZ75.json","view_paper":"https://pith.science/paper/NCZUDUJY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.12598&json=true","fetch_graph":"https://pith.science/api/pith-number/NCZUDUJYVSRNTG4CNSHPWCSZ75/graph.json","fetch_events":"https://pith.science/api/pith-number/NCZUDUJYVSRNTG4CNSHPWCSZ75/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NCZUDUJYVSRNTG4CNSHPWCSZ75/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NCZUDUJYVSRNTG4CNSHPWCSZ75/action/storage_attestation","attest_author":"https://pith.science/pith/NCZUDUJYVSRNTG4CNSHPWCSZ75/action/author_attestation","sign_citation":"https://pith.science/pith/NCZUDUJYVSRNTG4CNSHPWCSZ75/action/citation_signature","submit_replication":"https://pith.science/pith/NCZUDUJYVSRNTG4CNSHPWCSZ75/action/replication_record"}},"created_at":"2026-07-05T11:21:56.149594+00:00","updated_at":"2026-07-05T11:21:56.149594+00:00"}