{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MIUL55RASQ2S4POYTLGWZI4VPS","short_pith_number":"pith:MIUL55RA","schema_version":"1.0","canonical_sha256":"6228bef62094352e3dd89acd6ca3957c9d5cbe00f2045631ae102c02b278ab7e","source":{"kind":"arxiv","id":"2404.18322","version":2},"attestation_state":"computed","paper":{"title":"BlockLLM: Multi-tenant Finer-grained Serving for Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DC","authors_text":"Aditya Akella, Akshay Jajoo, Bodun Hu, Geon-Woo Kim, Hong Xu, Jiamin Li, Le Xu, Myungjin Lee","submitted_at":"2024-04-28T21:23:40Z","abstract_excerpt":"The increasing demand for Large Language Models (LLMs) across various applications has led to a significant shift in the design of deep learning serving systems. Deploying LLMs, particularly in multi-tenant environments, poses substantial challenges due to their high computational and memory demands. We introduce BlockLLM, a serving system that leverages component sharing among fine-tuned LLM models to provide an efficient and flexible solution for LLM workloads. BlockLLM partitions models into finer-grained blocks, enabling the reuse of model components and independent provisioning to improve"},"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":"2404.18322","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2024-04-28T21:23:40Z","cross_cats_sorted":[],"title_canon_sha256":"3f9d4cb53b18b719b1791ee1edfb7d196018e02d6cd6cb06fe9da522366ad564","abstract_canon_sha256":"45021970b39c31577de8daf027328158d3e41b31bdcb8a6cfa24c2c63bd78c6d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:10:46.852443Z","signature_b64":"8pydermG50u94uQ7Qwtkjuhb1J7rHsxffvt6To2WCHZ0UfyaXwYX/2aRV0hrdwrerO1QKu1d3E9ZgDodSqiaCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6228bef62094352e3dd89acd6ca3957c9d5cbe00f2045631ae102c02b278ab7e","last_reissued_at":"2026-07-05T09:10:46.851936Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:10:46.851936Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BlockLLM: Multi-tenant Finer-grained Serving for Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DC","authors_text":"Aditya Akella, Akshay Jajoo, Bodun Hu, Geon-Woo Kim, Hong Xu, Jiamin Li, Le Xu, Myungjin Lee","submitted_at":"2024-04-28T21:23:40Z","abstract_excerpt":"The increasing demand for Large Language Models (LLMs) across various applications has led to a significant shift in the design of deep learning serving systems. Deploying LLMs, particularly in multi-tenant environments, poses substantial challenges due to their high computational and memory demands. We introduce BlockLLM, a serving system that leverages component sharing among fine-tuned LLM models to provide an efficient and flexible solution for LLM workloads. BlockLLM partitions models into finer-grained blocks, enabling the reuse of model components and independent provisioning to improve"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.18322","kind":"arxiv","version":2},"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/2404.18322/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":"2404.18322","created_at":"2026-07-05T09:10:46.851990+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.18322v2","created_at":"2026-07-05T09:10:46.851990+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.18322","created_at":"2026-07-05T09:10:46.851990+00:00"},{"alias_kind":"pith_short_12","alias_value":"MIUL55RASQ2S","created_at":"2026-07-05T09:10:46.851990+00:00"},{"alias_kind":"pith_short_16","alias_value":"MIUL55RASQ2S4POY","created_at":"2026-07-05T09:10:46.851990+00:00"},{"alias_kind":"pith_short_8","alias_value":"MIUL55RA","created_at":"2026-07-05T09:10:46.851990+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2502.02970","citing_title":"Distributional Statistics Restore Training Data Auditability in One-step Distilled Diffusion Models","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2510.11938","citing_title":"FlexPipe: Adapting Dynamic LLM Serving Through Inflight Pipeline Refactoring in Fragmented Serverless Clusters","ref_index":20,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MIUL55RASQ2S4POYTLGWZI4VPS","json":"https://pith.science/pith/MIUL55RASQ2S4POYTLGWZI4VPS.json","graph_json":"https://pith.science/api/pith-number/MIUL55RASQ2S4POYTLGWZI4VPS/graph.json","events_json":"https://pith.science/api/pith-number/MIUL55RASQ2S4POYTLGWZI4VPS/events.json","paper":"https://pith.science/paper/MIUL55RA"},"agent_actions":{"view_html":"https://pith.science/pith/MIUL55RASQ2S4POYTLGWZI4VPS","download_json":"https://pith.science/pith/MIUL55RASQ2S4POYTLGWZI4VPS.json","view_paper":"https://pith.science/paper/MIUL55RA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.18322&json=true","fetch_graph":"https://pith.science/api/pith-number/MIUL55RASQ2S4POYTLGWZI4VPS/graph.json","fetch_events":"https://pith.science/api/pith-number/MIUL55RASQ2S4POYTLGWZI4VPS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MIUL55RASQ2S4POYTLGWZI4VPS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MIUL55RASQ2S4POYTLGWZI4VPS/action/storage_attestation","attest_author":"https://pith.science/pith/MIUL55RASQ2S4POYTLGWZI4VPS/action/author_attestation","sign_citation":"https://pith.science/pith/MIUL55RASQ2S4POYTLGWZI4VPS/action/citation_signature","submit_replication":"https://pith.science/pith/MIUL55RASQ2S4POYTLGWZI4VPS/action/replication_record"}},"created_at":"2026-07-05T09:10:46.851990+00:00","updated_at":"2026-07-05T09:10:46.851990+00:00"}