{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:PLM7XXZ72GVFDCRLJTVQFT432U","short_pith_number":"pith:PLM7XXZ7","schema_version":"1.0","canonical_sha256":"7ad9fbdf3fd1aa518a2b4ceb02cf9bd53c925e5964c66a1c100c9805accc8057","source":{"kind":"arxiv","id":"2502.08145","version":1},"attestation_state":"computed","paper":{"title":"Democratizing AI: Open-source Scalable LLM Training on GPU-based Supercomputers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.DC"],"primary_cat":"cs.LG","authors_text":"Abhimanyu Hans, Abhinav Bhatele, Aditya Ranjan, Aditya Tomar, John Kirchenbauer, Jonas Geiping, Manli Shu, Neel Jain, Prajwal Singhania, Siddharth Singh, Tom Goldstein, Yuxin Wen","submitted_at":"2025-02-12T06:05:52Z","abstract_excerpt":"Training and fine-tuning large language models (LLMs) with hundreds of billions to trillions of parameters requires tens of thousands of GPUs, and a highly scalable software stack. In this work, we present a novel four-dimensional hybrid parallel algorithm implemented in a highly scalable, portable, open-source framework called AxoNN. We describe several performance optimizations in AxoNN to improve matrix multiply kernel performance, overlap non-blocking collectives with computation, and performance modeling to choose performance optimal configurations. These have resulted in unprecedented sc"},"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":"2502.08145","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-12T06:05:52Z","cross_cats_sorted":["cs.AI","cs.DC"],"title_canon_sha256":"43d69261c20ae8ae327e250a07cac55d6fc5c568ddb8c4c574c2df16f2d64c94","abstract_canon_sha256":"8b7b8e76955058437b6cbe2ff10c934bff329d6b0c0ff967da528fdb848216a5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:13:16.160258Z","signature_b64":"56XOh05caOSjvI399eXCrkaCFMropLO/rk/XPWL/Hig1WUwmr8mQMbpXktXY0KqgifjaoPcCOGLWvgsmI4gtCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7ad9fbdf3fd1aa518a2b4ceb02cf9bd53c925e5964c66a1c100c9805accc8057","last_reissued_at":"2026-07-05T10:13:16.159775Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:13:16.159775Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Democratizing AI: Open-source Scalable LLM Training on GPU-based Supercomputers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.DC"],"primary_cat":"cs.LG","authors_text":"Abhimanyu Hans, Abhinav Bhatele, Aditya Ranjan, Aditya Tomar, John Kirchenbauer, Jonas Geiping, Manli Shu, Neel Jain, Prajwal Singhania, Siddharth Singh, Tom Goldstein, Yuxin Wen","submitted_at":"2025-02-12T06:05:52Z","abstract_excerpt":"Training and fine-tuning large language models (LLMs) with hundreds of billions to trillions of parameters requires tens of thousands of GPUs, and a highly scalable software stack. In this work, we present a novel four-dimensional hybrid parallel algorithm implemented in a highly scalable, portable, open-source framework called AxoNN. We describe several performance optimizations in AxoNN to improve matrix multiply kernel performance, overlap non-blocking collectives with computation, and performance modeling to choose performance optimal configurations. These have resulted in unprecedented sc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.08145","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/2502.08145/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":"2502.08145","created_at":"2026-07-05T10:13:16.159854+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.08145v1","created_at":"2026-07-05T10:13:16.159854+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.08145","created_at":"2026-07-05T10:13:16.159854+00:00"},{"alias_kind":"pith_short_12","alias_value":"PLM7XXZ72GVF","created_at":"2026-07-05T10:13:16.159854+00:00"},{"alias_kind":"pith_short_16","alias_value":"PLM7XXZ72GVFDCRL","created_at":"2026-07-05T10:13:16.159854+00:00"},{"alias_kind":"pith_short_8","alias_value":"PLM7XXZ7","created_at":"2026-07-05T10:13:16.159854+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/PLM7XXZ72GVFDCRLJTVQFT432U","json":"https://pith.science/pith/PLM7XXZ72GVFDCRLJTVQFT432U.json","graph_json":"https://pith.science/api/pith-number/PLM7XXZ72GVFDCRLJTVQFT432U/graph.json","events_json":"https://pith.science/api/pith-number/PLM7XXZ72GVFDCRLJTVQFT432U/events.json","paper":"https://pith.science/paper/PLM7XXZ7"},"agent_actions":{"view_html":"https://pith.science/pith/PLM7XXZ72GVFDCRLJTVQFT432U","download_json":"https://pith.science/pith/PLM7XXZ72GVFDCRLJTVQFT432U.json","view_paper":"https://pith.science/paper/PLM7XXZ7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.08145&json=true","fetch_graph":"https://pith.science/api/pith-number/PLM7XXZ72GVFDCRLJTVQFT432U/graph.json","fetch_events":"https://pith.science/api/pith-number/PLM7XXZ72GVFDCRLJTVQFT432U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PLM7XXZ72GVFDCRLJTVQFT432U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PLM7XXZ72GVFDCRLJTVQFT432U/action/storage_attestation","attest_author":"https://pith.science/pith/PLM7XXZ72GVFDCRLJTVQFT432U/action/author_attestation","sign_citation":"https://pith.science/pith/PLM7XXZ72GVFDCRLJTVQFT432U/action/citation_signature","submit_replication":"https://pith.science/pith/PLM7XXZ72GVFDCRLJTVQFT432U/action/replication_record"}},"created_at":"2026-07-05T10:13:16.159854+00:00","updated_at":"2026-07-05T10:13:16.159854+00:00"}