{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:TGPSSDHLQQZXCIQHDN6TA5UTNQ","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":"46fe8828dc7937ec4b598c842259430d355a384666314b65dd1fe0b71c004a4e","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2024-11-04T04:15:36Z","title_canon_sha256":"66d84f63683bd4ad312b0c106e4702ff532eb6ca8a58cc31907910ee0f09d91f"},"schema_version":"1.0","source":{"id":"2411.01783","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.01783","created_at":"2026-07-05T10:51:27Z"},{"alias_kind":"arxiv_version","alias_value":"2411.01783v3","created_at":"2026-07-05T10:51:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.01783","created_at":"2026-07-05T10:51:27Z"},{"alias_kind":"pith_short_12","alias_value":"TGPSSDHLQQZX","created_at":"2026-07-05T10:51:27Z"},{"alias_kind":"pith_short_16","alias_value":"TGPSSDHLQQZXCIQH","created_at":"2026-07-05T10:51:27Z"},{"alias_kind":"pith_short_8","alias_value":"TGPSSDHL","created_at":"2026-07-05T10:51:27Z"}],"graph_snapshots":[{"event_id":"sha256:3b491af5f14c23a0ae5efd833a2afddfa0d8f88949db13d2ad7007d0295fb272","target":"graph","created_at":"2026-07-05T10:51:27Z","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/2411.01783/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present context parallelism for long-context large language model inference, which achieves near-linear scaling for long-context prefill latency with up to 128 H100 GPUs across 16 nodes. Particularly, our method achieves 1M context prefill with Llama3 405B model in 77s (93% parallelization efficiency, 63% FLOPS utilization) and 128K context prefill in 3.8s. We develop two lossless exact ring attention variants: pass-KV and pass-Q to cover a wide range of use cases with the state-of-the-art performance: full prefill, persistent KV prefill and decode. Benchmarks on H100 GPU hosts inter-connec","authors_text":"Amy Yang, Aya Ibrahim, Bangsheng Tang, Grigory Sizov, Jeremy Reizenstein, Jianyu Huang, Jingyi Yang, Jongsoo Park, Xinfeng Xie","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2024-11-04T04:15:36Z","title":"Context Parallelism for Scalable Million-Token Inference"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.01783","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":"sha256:879e1df0b7ebeb6bf5e3c92e8806a777dfd2dd91a5b9698a9366903b60dcfac6","target":"record","created_at":"2026-07-05T10:51:27Z","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":"46fe8828dc7937ec4b598c842259430d355a384666314b65dd1fe0b71c004a4e","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2024-11-04T04:15:36Z","title_canon_sha256":"66d84f63683bd4ad312b0c106e4702ff532eb6ca8a58cc31907910ee0f09d91f"},"schema_version":"1.0","source":{"id":"2411.01783","kind":"arxiv","version":3}},"canonical_sha256":"999f290ceb84337122071b7d3076936c09407561bd6f7a70ef2d89dd4428d80d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"999f290ceb84337122071b7d3076936c09407561bd6f7a70ef2d89dd4428d80d","first_computed_at":"2026-07-05T10:51:27.856924Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:51:27.856924Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mPuGAbGNA+s8A6Qz+wtTWPKqaaZdedcaiKPhDI+WS4WD9cxJpazhiK8eGhdlaNhgNSozxho45/LtBphXtFknBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:51:27.857409Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.01783","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:879e1df0b7ebeb6bf5e3c92e8806a777dfd2dd91a5b9698a9366903b60dcfac6","sha256:3b491af5f14c23a0ae5efd833a2afddfa0d8f88949db13d2ad7007d0295fb272"],"state_sha256":"f9a58abbf316b869015a0058b41e340186a9ae5a187c16ea1142ddae9fac8fcf"}