{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:RB763DXV7MR7DQSHKAX73AEARM","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":"e07b2db0f88e8f24bb9268b02825b3a173ad8ef351279b1b18d2e7871a40a52e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.DC","submitted_at":"2025-06-27T09:27:04Z","title_canon_sha256":"36803eb871ef2cc017577ec62ac39951845562dbe7625e864771cad61bc66f75"},"schema_version":"1.0","source":{"id":"2506.22033","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.22033","created_at":"2026-07-05T11:28:20Z"},{"alias_kind":"arxiv_version","alias_value":"2506.22033v1","created_at":"2026-07-05T11:28:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.22033","created_at":"2026-07-05T11:28:20Z"},{"alias_kind":"pith_short_12","alias_value":"RB763DXV7MR7","created_at":"2026-07-05T11:28:20Z"},{"alias_kind":"pith_short_16","alias_value":"RB763DXV7MR7DQSH","created_at":"2026-07-05T11:28:20Z"},{"alias_kind":"pith_short_8","alias_value":"RB763DXV","created_at":"2026-07-05T11:28:20Z"}],"graph_snapshots":[{"event_id":"sha256:c31d1687e4965474a13231557d3bc0a9e14fd28af942731e3c07fbe35c5d130d","target":"graph","created_at":"2026-07-05T11:28:20Z","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/2506.22033/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As inference workloads for large language models (LLMs) scale to meet growing user demand, pipeline parallelism (PP) has become a widely adopted strategy for multi-GPU deployment, particularly in cross-node setups, to improve key-value (KV) cache capacity and inference throughput. However, PP suffers from inherent inefficiencies caused by three types of execution bubbles-load-imbalance, intra-stage, and inter-stage-which limit pipeline saturation. We present SiPipe, a heterogeneous pipeline design that improves throughput by leveraging underutilized CPU resources to offload auxiliary computati","authors_text":"Bohan Zhao, Yongchao He, Zheng Cao","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.DC","submitted_at":"2025-06-27T09:27:04Z","title":"SiPipe: Bridging the CPU-GPU Utilization Gap for Efficient Pipeline-Parallel LLM Inference"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.22033","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:f0aa49e4a5b7b421cceacf0f46a6b1a803f291f4a0faca593f2a86bd102693f2","target":"record","created_at":"2026-07-05T11:28:20Z","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":"e07b2db0f88e8f24bb9268b02825b3a173ad8ef351279b1b18d2e7871a40a52e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.DC","submitted_at":"2025-06-27T09:27:04Z","title_canon_sha256":"36803eb871ef2cc017577ec62ac39951845562dbe7625e864771cad61bc66f75"},"schema_version":"1.0","source":{"id":"2506.22033","kind":"arxiv","version":1}},"canonical_sha256":"887fed8ef5fb23f1c247502ffd80808b073b549ca142aa9cec571458cd930124","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"887fed8ef5fb23f1c247502ffd80808b073b549ca142aa9cec571458cd930124","first_computed_at":"2026-07-05T11:28:20.815294Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:28:20.815294Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZqUIRMeshNounLIryY0D3f5Hco31XwB58zd5buzdj8SWfMl44fPtmwlqlcXICgUSYyojNm2Piz61ESybhUU6Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T11:28:20.815791Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.22033","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f0aa49e4a5b7b421cceacf0f46a6b1a803f291f4a0faca593f2a86bd102693f2","sha256:c31d1687e4965474a13231557d3bc0a9e14fd28af942731e3c07fbe35c5d130d"],"state_sha256":"9d800fc0a63d77d0d69e657f34c2f9b02f92ad167c73188bcc20f81127bd0829"}