{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:PDTFYEYEMOXT7OLWEMXNAYRJIE","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":"652dc9b97c489d19086530ce206823cdad9700123b701a71efce41b0c601fdda","cross_cats_sorted":["cs.DC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-08-10T06:16:24Z","title_canon_sha256":"fd482f33bafc1e38aa450ac474036fc105e808ac7ca32cc41d2081ca3a63b6b8"},"schema_version":"1.0","source":{"id":"2608.09160","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.09160","created_at":"2026-08-11T02:21:56Z"},{"alias_kind":"arxiv_version","alias_value":"2608.09160v1","created_at":"2026-08-11T02:21:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.09160","created_at":"2026-08-11T02:21:56Z"},{"alias_kind":"pith_short_12","alias_value":"PDTFYEYEMOXT","created_at":"2026-08-11T02:21:56Z"},{"alias_kind":"pith_short_16","alias_value":"PDTFYEYEMOXT7OLW","created_at":"2026-08-11T02:21:56Z"},{"alias_kind":"pith_short_8","alias_value":"PDTFYEYE","created_at":"2026-08-11T02:21:56Z"}],"graph_snapshots":[{"event_id":"sha256:44154c828035f3773642ed2c8e371971237ad7d571fe531a3d9792df55f2998c","target":"graph","created_at":"2026-08-11T02:21:56Z","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/2608.09160/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Query-Key Normalization (QK-Norm) improves the training stability and quality of modern Large Language Models (LLMs). However, under Tensor Parallelism (TP), layerwise QK-Norm introduces additional cross-GPU communication because the normalization factor depends on the full hidden vector. We present SwiftQK, a multi-GPU RMSNorm kernel that exchanges only scalar normalization statistics and overlaps the remaining Peer-to-Peer reduction with independent element-wise computation in a deadlock-safe persistent kernel. Evaluations on recent LLMs show that SwiftQK reduces QK-Norm latency by 81.4--93.","authors_text":"Gyudong Kim, Wonjun Han, Young Geun Kim","cross_cats":["cs.DC"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-08-10T06:16:24Z","title":"SwiftQK: Fast and Communication-Efficient Tensor Parallelism for Query-Key Normalization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.09160","kind":"arxiv","version":1},"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":"sha256:7268c0c851cc3c2039727ca470288e29d22f9a2ed212f34781a4b47fd5561344","target":"record","created_at":"2026-08-11T02:21:56Z","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":"652dc9b97c489d19086530ce206823cdad9700123b701a71efce41b0c601fdda","cross_cats_sorted":["cs.DC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-08-10T06:16:24Z","title_canon_sha256":"fd482f33bafc1e38aa450ac474036fc105e808ac7ca32cc41d2081ca3a63b6b8"},"schema_version":"1.0","source":{"id":"2608.09160","kind":"arxiv","version":1}},"canonical_sha256":"78e65c130463af3fb976232ed0622941020e798628daf2f91162f7425f986438","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"78e65c130463af3fb976232ed0622941020e798628daf2f91162f7425f986438","first_computed_at":"2026-08-11T02:21:56.731881Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-11T02:21:56.731881Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LJcOz5tlWQxIIfuQrZsXshavbdGXKKfCX4mtOGun8ryRBecbxKMoUPxjSkdfH/h8OLzCVEQj0NcQWizFTb1WCQ==","signature_status":"signed_v1","signed_at":"2026-08-11T02:21:56.733244Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.09160","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7268c0c851cc3c2039727ca470288e29d22f9a2ed212f34781a4b47fd5561344","sha256:44154c828035f3773642ed2c8e371971237ad7d571fe531a3d9792df55f2998c"],"state_sha256":"47a495f3bf169b4323b6c57badf74d39d089377d8f3c8a734b90a5e9fb4a043d"}