{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:PSTPD2UCT3FQXNQW5CCNJFVWK3","short_pith_number":"pith:PSTPD2UC","schema_version":"1.0","canonical_sha256":"7ca6f1ea829ecb0bb616e884d496b656dfa0345cfbadfc68d7502695576f105c","source":{"kind":"arxiv","id":"2310.16355","version":3},"attestation_state":"computed","paper":{"title":"RedCoast: A Lightweight Tool to Automate Distributed Training of LLMs on Any GPU/TPUs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bowen Tan, Eric Xing, Hongyi Wang, Jindong Chen, Lijuan Liu, Yonghao Zhuang, Yun Zhu, Zhiting Hu","submitted_at":"2023-10-25T04:32:35Z","abstract_excerpt":"The recent progress of AI can be largely attributed to large language models (LLMs). However, their escalating memory requirements introduce challenges for machine learning (ML) researchers and engineers. Addressing this requires developers to partition a large model to distribute it across multiple GPUs or TPUs. This necessitates considerable coding and intricate configuration efforts with existing model parallel tools, such as Megatron-LM, DeepSpeed, and Alpa. These tools require users' expertise in machine learning systems (MLSys), creating a bottleneck in LLM development, particularly for "},"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":"2310.16355","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-25T04:32:35Z","cross_cats_sorted":[],"title_canon_sha256":"f9f6f52baad0bd770287934ac5c05f5ab1755aa6eb3c05345ebc18bc1c35d061","abstract_canon_sha256":"d834b516853706ad96a96bcbf5d9958b6b2e58ee6a5524591adcf77a29df1342"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:31:06.522734Z","signature_b64":"cFCVsL8BiP2iEJr8cUepsFIh/kHEQx6bLAf+UlWAfaulHFuimNUTnY14kxMs412gnjY9h03QR/x4PciMMALQCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7ca6f1ea829ecb0bb616e884d496b656dfa0345cfbadfc68d7502695576f105c","last_reissued_at":"2026-07-05T08:31:06.522340Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:31:06.522340Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RedCoast: A Lightweight Tool to Automate Distributed Training of LLMs on Any GPU/TPUs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bowen Tan, Eric Xing, Hongyi Wang, Jindong Chen, Lijuan Liu, Yonghao Zhuang, Yun Zhu, Zhiting Hu","submitted_at":"2023-10-25T04:32:35Z","abstract_excerpt":"The recent progress of AI can be largely attributed to large language models (LLMs). However, their escalating memory requirements introduce challenges for machine learning (ML) researchers and engineers. Addressing this requires developers to partition a large model to distribute it across multiple GPUs or TPUs. This necessitates considerable coding and intricate configuration efforts with existing model parallel tools, such as Megatron-LM, DeepSpeed, and Alpa. These tools require users' expertise in machine learning systems (MLSys), creating a bottleneck in LLM development, particularly for "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.16355","kind":"arxiv","version":3},"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/2310.16355/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":"2310.16355","created_at":"2026-07-05T08:31:06.522398+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.16355v3","created_at":"2026-07-05T08:31:06.522398+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.16355","created_at":"2026-07-05T08:31:06.522398+00:00"},{"alias_kind":"pith_short_12","alias_value":"PSTPD2UCT3FQ","created_at":"2026-07-05T08:31:06.522398+00:00"},{"alias_kind":"pith_short_16","alias_value":"PSTPD2UCT3FQXNQW","created_at":"2026-07-05T08:31:06.522398+00:00"},{"alias_kind":"pith_short_8","alias_value":"PSTPD2UC","created_at":"2026-07-05T08:31:06.522398+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/PSTPD2UCT3FQXNQW5CCNJFVWK3","json":"https://pith.science/pith/PSTPD2UCT3FQXNQW5CCNJFVWK3.json","graph_json":"https://pith.science/api/pith-number/PSTPD2UCT3FQXNQW5CCNJFVWK3/graph.json","events_json":"https://pith.science/api/pith-number/PSTPD2UCT3FQXNQW5CCNJFVWK3/events.json","paper":"https://pith.science/paper/PSTPD2UC"},"agent_actions":{"view_html":"https://pith.science/pith/PSTPD2UCT3FQXNQW5CCNJFVWK3","download_json":"https://pith.science/pith/PSTPD2UCT3FQXNQW5CCNJFVWK3.json","view_paper":"https://pith.science/paper/PSTPD2UC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.16355&json=true","fetch_graph":"https://pith.science/api/pith-number/PSTPD2UCT3FQXNQW5CCNJFVWK3/graph.json","fetch_events":"https://pith.science/api/pith-number/PSTPD2UCT3FQXNQW5CCNJFVWK3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PSTPD2UCT3FQXNQW5CCNJFVWK3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PSTPD2UCT3FQXNQW5CCNJFVWK3/action/storage_attestation","attest_author":"https://pith.science/pith/PSTPD2UCT3FQXNQW5CCNJFVWK3/action/author_attestation","sign_citation":"https://pith.science/pith/PSTPD2UCT3FQXNQW5CCNJFVWK3/action/citation_signature","submit_replication":"https://pith.science/pith/PSTPD2UCT3FQXNQW5CCNJFVWK3/action/replication_record"}},"created_at":"2026-07-05T08:31:06.522398+00:00","updated_at":"2026-07-05T08:31:06.522398+00:00"}