{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:LOYYHJXGUAHVIZJBIEZZNKB42K","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":"c2536bc15688faf1c290c650afef2f178baf7161bbe152ab7b1b7194db581e4b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2024-01-17T11:47:59Z","title_canon_sha256":"797785b0998bdcf271fc638d3a3e7b606268f72f6d1619732bb3ec043a24e703"},"schema_version":"1.0","source":{"id":"2401.09149","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.09149","created_at":"2026-07-05T07:36:05Z"},{"alias_kind":"arxiv_version","alias_value":"2401.09149v3","created_at":"2026-07-05T07:36:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.09149","created_at":"2026-07-05T07:36:05Z"},{"alias_kind":"pith_short_12","alias_value":"LOYYHJXGUAHV","created_at":"2026-07-05T07:36:05Z"},{"alias_kind":"pith_short_16","alias_value":"LOYYHJXGUAHVIZJB","created_at":"2026-07-05T07:36:05Z"},{"alias_kind":"pith_short_8","alias_value":"LOYYHJXG","created_at":"2026-07-05T07:36:05Z"}],"graph_snapshots":[{"event_id":"sha256:b20b3cd56b3f5df53f716acb39373e9ec761962ec8ce7496a1a1f530783506b4","target":"graph","created_at":"2026-07-05T07:36:05Z","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/2401.09149/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) with long sequences begin to power more and more fundamentally new applications we use every day. Existing methods for long-sequence LLM training are neither efficient nor compatible with commonly-used training algorithms such as FlashAttention. We design InternEvo to address these issues. InternEvo decouples all of the sharding dimensions into a new hierarchical space, and systematically analyzes the memory and communication cost of LLM training. Then, it generates an effective hybrid parallelism strategy. We design a new selective overlap mechanism to mitigate th","authors_text":"Diandian Gu, Guoteng Wang, Peng Sun, Qiaoling Chen, Qinghao Hu, Tianwei Zhang, Ting Huang, Xin Jin, Xun Chen, Yingtong Xiong, Yonggang Wen","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2024-01-17T11:47:59Z","title":"InternEvo: Efficient Long-sequence Large Language Model Training via Hybrid Parallelism and Redundant Sharding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.09149","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":"sha256:547090fa0b8ada064120dfb1f1240451ca0b80db2dcd21db96ba39a7eb5ad728","target":"record","created_at":"2026-07-05T07:36:05Z","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":"c2536bc15688faf1c290c650afef2f178baf7161bbe152ab7b1b7194db581e4b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2024-01-17T11:47:59Z","title_canon_sha256":"797785b0998bdcf271fc638d3a3e7b606268f72f6d1619732bb3ec043a24e703"},"schema_version":"1.0","source":{"id":"2401.09149","kind":"arxiv","version":3}},"canonical_sha256":"5bb183a6e6a00f546521413396a83cd28ed2093ed113161d8c096f9001e85363","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5bb183a6e6a00f546521413396a83cd28ed2093ed113161d8c096f9001e85363","first_computed_at":"2026-07-05T07:36:05.959321Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:36:05.959321Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2xqR+qwKzOR9Y445fE8RSIGwfYzILEwj1igIAh36pAc8PRE6jdsjlj2kRp+s/OJTqFPhGsDtYphT5rL9ZuB+Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:36:05.959799Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.09149","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:547090fa0b8ada064120dfb1f1240451ca0b80db2dcd21db96ba39a7eb5ad728","sha256:b20b3cd56b3f5df53f716acb39373e9ec761962ec8ce7496a1a1f530783506b4"],"state_sha256":"0aea3fb43bcee104732bcb4debbf91074e0ed31f8b6c62c2a674ba78e338c8aa"}