{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:DJIJXEEZRMJY66ZCNW47KAC4JH","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":"c549b6459afe71638a6d61b146d1765deade48476c6884c67f7629745ee3e05d","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.DC","submitted_at":"2025-02-28T05:20:48Z","title_canon_sha256":"305d756a2529fb22994d56e7411254846268020a1bd7712afab3ab339278ae86"},"schema_version":"1.0","source":{"id":"2502.20727","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.20727","created_at":"2026-07-05T11:13:21Z"},{"alias_kind":"arxiv_version","alias_value":"2502.20727v4","created_at":"2026-07-05T11:13:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.20727","created_at":"2026-07-05T11:13:21Z"},{"alias_kind":"pith_short_12","alias_value":"DJIJXEEZRMJY","created_at":"2026-07-05T11:13:21Z"},{"alias_kind":"pith_short_16","alias_value":"DJIJXEEZRMJY66ZC","created_at":"2026-07-05T11:13:21Z"},{"alias_kind":"pith_short_8","alias_value":"DJIJXEEZ","created_at":"2026-07-05T11:13:21Z"}],"graph_snapshots":[{"event_id":"sha256:263271d87c7f9171757f5a0984af1f54c6b6a39287796d8cff1de715b1b38739","target":"graph","created_at":"2026-07-05T11:13:21Z","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/2502.20727/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"With the rapid expansion in the scale of large language models (LLMs), enabling efficient distributed inference across multiple computing units has become increasingly critical. However, communication overheads from popular distributed inference techniques such as Tensor Parallelism pose a significant challenge to achieve scalability and low latency. Therefore, we introduce a novel optimization technique, Sync-Point Drop (SPD), to reduce communication overheads in tensor parallelism by selectively dropping synchronization on attention outputs. In detail, we first propose a block design that al","authors_text":"Arnav Kundu, Duc Hoang, Han-Byul Kim, Minsik Cho, Mohammad Samragh","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.DC","submitted_at":"2025-02-28T05:20:48Z","title":"SPD: Sync-Point Drop for Efficient Tensor Parallelism of Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.20727","kind":"arxiv","version":4},"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":"sha256:12fdce7e267f8bee8ffcfb2fb9c5110cfbd037847fae23f0befd4e9a8fcf8e74","target":"record","created_at":"2026-07-05T11:13:21Z","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":"c549b6459afe71638a6d61b146d1765deade48476c6884c67f7629745ee3e05d","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.DC","submitted_at":"2025-02-28T05:20:48Z","title_canon_sha256":"305d756a2529fb22994d56e7411254846268020a1bd7712afab3ab339278ae86"},"schema_version":"1.0","source":{"id":"2502.20727","kind":"arxiv","version":4}},"canonical_sha256":"1a509b90998b138f7b226db9f5005c49cba5477511102f63595abf8498fce016","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1a509b90998b138f7b226db9f5005c49cba5477511102f63595abf8498fce016","first_computed_at":"2026-07-05T11:13:21.670203Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:13:21.670203Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fiXmVnaV1lKObqSg2TSMKPprDyoYfo7k/k/utu3oSYC544vgDBz8p1XWHl7io6P6lhKEjSEcAzEEf7+4eqFEAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:13:21.670728Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.20727","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:12fdce7e267f8bee8ffcfb2fb9c5110cfbd037847fae23f0befd4e9a8fcf8e74","sha256:263271d87c7f9171757f5a0984af1f54c6b6a39287796d8cff1de715b1b38739"],"state_sha256":"800fd8850ea79bf56a3af7ed0bbb7520caddbe1155e5c9ef9e0dc44ce253e1b0"}