{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:REKYWRLSAOG72RLVASVPAOYQ5W","short_pith_number":"pith:REKYWRLS","schema_version":"1.0","canonical_sha256":"89158b4572038dfd457504aaf03b10ed92bae519f00678fdd8faa708427dd541","source":{"kind":"arxiv","id":"2111.14255","version":1},"attestation_state":"computed","paper":{"title":"Automated Runtime-Aware Scheduling for Multi-Tenant DNN Inference on GPU","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DC","authors_text":"Chenchen Liu, Di Wang, Fuxun Yu, Longfei Shangguan, Shawn Bray, Xiang Chen, Xulong Tang","submitted_at":"2021-11-28T22:43:13Z","abstract_excerpt":"With the fast development of deep neural networks (DNNs), many real-world applications are adopting multiple models to conduct compound tasks, such as co-running classification, detection, and segmentation models on autonomous vehicles. Such multi-tenant DNN inference cases greatly exacerbate the computational complexity and call for comprehensive collaboration for graph-level operator scheduling, runtime-level resource awareness, as well as hardware scheduler support. However, the current scheduling support for such multi-tenant inference is still relatively backward. In this work, we propose"},"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":"2111.14255","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2021-11-28T22:43:13Z","cross_cats_sorted":[],"title_canon_sha256":"1daff4f5f3fe745e18a201ae835936304d210146944c94f4270137334e38aab4","abstract_canon_sha256":"217487b2dad31ea4655195fc9e0b83f19330ea8b5c62c08cca32c8f07834eb42"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:35:40.852193Z","signature_b64":"d2uTi96Pxgq7oV0X/6T9AfPWrpAksNUL4D7fOxbweMzAtIMnnyIzIxh4Hlw1IMrD1zsqP0tiT4eGoVNUbYkKDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"89158b4572038dfd457504aaf03b10ed92bae519f00678fdd8faa708427dd541","last_reissued_at":"2026-07-05T03:35:40.851756Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:35:40.851756Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Automated Runtime-Aware Scheduling for Multi-Tenant DNN Inference on GPU","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DC","authors_text":"Chenchen Liu, Di Wang, Fuxun Yu, Longfei Shangguan, Shawn Bray, Xiang Chen, Xulong Tang","submitted_at":"2021-11-28T22:43:13Z","abstract_excerpt":"With the fast development of deep neural networks (DNNs), many real-world applications are adopting multiple models to conduct compound tasks, such as co-running classification, detection, and segmentation models on autonomous vehicles. Such multi-tenant DNN inference cases greatly exacerbate the computational complexity and call for comprehensive collaboration for graph-level operator scheduling, runtime-level resource awareness, as well as hardware scheduler support. However, the current scheduling support for such multi-tenant inference is still relatively backward. In this work, we propose"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.14255","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/2111.14255/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":"2111.14255","created_at":"2026-07-05T03:35:40.851813+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.14255v1","created_at":"2026-07-05T03:35:40.851813+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.14255","created_at":"2026-07-05T03:35:40.851813+00:00"},{"alias_kind":"pith_short_12","alias_value":"REKYWRLSAOG7","created_at":"2026-07-05T03:35:40.851813+00:00"},{"alias_kind":"pith_short_16","alias_value":"REKYWRLSAOG72RLV","created_at":"2026-07-05T03:35:40.851813+00:00"},{"alias_kind":"pith_short_8","alias_value":"REKYWRLS","created_at":"2026-07-05T03:35:40.851813+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/REKYWRLSAOG72RLVASVPAOYQ5W","json":"https://pith.science/pith/REKYWRLSAOG72RLVASVPAOYQ5W.json","graph_json":"https://pith.science/api/pith-number/REKYWRLSAOG72RLVASVPAOYQ5W/graph.json","events_json":"https://pith.science/api/pith-number/REKYWRLSAOG72RLVASVPAOYQ5W/events.json","paper":"https://pith.science/paper/REKYWRLS"},"agent_actions":{"view_html":"https://pith.science/pith/REKYWRLSAOG72RLVASVPAOYQ5W","download_json":"https://pith.science/pith/REKYWRLSAOG72RLVASVPAOYQ5W.json","view_paper":"https://pith.science/paper/REKYWRLS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.14255&json=true","fetch_graph":"https://pith.science/api/pith-number/REKYWRLSAOG72RLVASVPAOYQ5W/graph.json","fetch_events":"https://pith.science/api/pith-number/REKYWRLSAOG72RLVASVPAOYQ5W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/REKYWRLSAOG72RLVASVPAOYQ5W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/REKYWRLSAOG72RLVASVPAOYQ5W/action/storage_attestation","attest_author":"https://pith.science/pith/REKYWRLSAOG72RLVASVPAOYQ5W/action/author_attestation","sign_citation":"https://pith.science/pith/REKYWRLSAOG72RLVASVPAOYQ5W/action/citation_signature","submit_replication":"https://pith.science/pith/REKYWRLSAOG72RLVASVPAOYQ5W/action/replication_record"}},"created_at":"2026-07-05T03:35:40.851813+00:00","updated_at":"2026-07-05T03:35:40.851813+00:00"}