{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:EXWTNCWIEC53LK2VFB2DIXR2XS","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":"fb8af0a59c8f586bab447715d2f20853ffc34a3bb8a45cee11be70e45919e932","cross_cats_sorted":["cs.AI","cs.DC","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AR","submitted_at":"2024-06-03T18:00:50Z","title_canon_sha256":"2bc67842eaf2472d09e6b9c428aee6ca1e65f882b30ce4a2247a1a10c90e53e9"},"schema_version":"1.0","source":{"id":"2406.01698","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.01698","created_at":"2026-07-05T11:03:14Z"},{"alias_kind":"arxiv_version","alias_value":"2406.01698v3","created_at":"2026-07-05T11:03:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.01698","created_at":"2026-07-05T11:03:14Z"},{"alias_kind":"pith_short_12","alias_value":"EXWTNCWIEC53","created_at":"2026-07-05T11:03:14Z"},{"alias_kind":"pith_short_16","alias_value":"EXWTNCWIEC53LK2V","created_at":"2026-07-05T11:03:14Z"},{"alias_kind":"pith_short_8","alias_value":"EXWTNCWI","created_at":"2026-07-05T11:03:14Z"}],"graph_snapshots":[{"event_id":"sha256:578e93934410609b044e86dcee85ad2ba7af55750e56b98ce43449cd09849ed6","target":"graph","created_at":"2026-07-05T11:03:14Z","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/2406.01698/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) have shown remarkable performance across a wide range of applications, often outperforming human experts. However, deploying these gigantic models efficiently for diverse inference use cases requires carefully designed hardware platforms with ample computing, memory, and network resources. With constant innovation in LLM serving optimizations and model architecture evolving at breakneck speed, the hardware requirements to meet Service Level Objectives (SLOs) remain an open research question.\n  To answer the question, we present an analytical tool, GenZ, to efficien","authors_text":"Abhimanyu Bambhaniya, Geonhwa Jeong, Madhu Kumar, Midhilesh Elavazhagan, Ritik Raj, Souvik Kundu, Sudarshan Srinivasan, Suvinay Subramanian, Tushar Krishna","cross_cats":["cs.AI","cs.DC","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AR","submitted_at":"2024-06-03T18:00:50Z","title":"Demystifying AI Platform Design for Distributed Inference of Next-Generation LLM models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.01698","kind":"arxiv","version":3},"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:d417326b1597c44f49ac679cc3aab7859d16ab9220fe6e1f99f928ad08540bd1","target":"record","created_at":"2026-07-05T11:03:14Z","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":"fb8af0a59c8f586bab447715d2f20853ffc34a3bb8a45cee11be70e45919e932","cross_cats_sorted":["cs.AI","cs.DC","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AR","submitted_at":"2024-06-03T18:00:50Z","title_canon_sha256":"2bc67842eaf2472d09e6b9c428aee6ca1e65f882b30ce4a2247a1a10c90e53e9"},"schema_version":"1.0","source":{"id":"2406.01698","kind":"arxiv","version":3}},"canonical_sha256":"25ed368ac820bbb5ab552874345e3abcab1371658a78623bf380a119b306863e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"25ed368ac820bbb5ab552874345e3abcab1371658a78623bf380a119b306863e","first_computed_at":"2026-07-05T11:03:14.980422Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:03:14.980422Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"v0yCPDd+ntpNMKWliMBLP8SLMmimxy8JuYlD9bDActW3CYMQuQmOVpriYOkHTUCsnhq38eAZHurZzN1X/TUyAw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:03:14.980898Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.01698","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d417326b1597c44f49ac679cc3aab7859d16ab9220fe6e1f99f928ad08540bd1","sha256:578e93934410609b044e86dcee85ad2ba7af55750e56b98ce43449cd09849ed6"],"state_sha256":"79c72ccc4bc22c5cc0ab3e786fefee592a75cf3728b0b86a830f477074207cf8"}