{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:65S4GNM5UTCCLYMFJ5OGED4EOP","short_pith_number":"pith:65S4GNM5","schema_version":"1.0","canonical_sha256":"f765c3359da4c425e1854f5c620f8473f157159651798a85c23ee3b6b112e355","source":{"kind":"arxiv","id":"2606.31093","version":1},"attestation_state":"computed","paper":{"title":"Omni-Flow: A Unified Workflow Orchestration and Distributed KV Cache Sharing Framework for Multimodal Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DC","authors_text":"Bin Xiao, Changran Wang, Jianping Lin, Jingfu Dong, Xiaoyu Zhao, Yitian Chen, Yuchen Xie, Yuqi Peng","submitted_at":"2026-06-30T03:29:21Z","abstract_excerpt":"As large language model (LLM) inference evolves from text-only to multimodal paradigms, inference systems face three challenges: (1) flexible orchestration of multimodal workflows, where heterogeneous computing units exhibit complex dependencies and concurrent control; (2) efficient transmission of massive intermediate data across processes and nodes, with tensors flowing at high speed among heterogeneous roles; and (3) efficient sharing of KV caches and model weights across roles to eliminate redundant GPU memory. Existing solutions deploy LLMs and diffusion models independently, lacking a sy"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2606.31093","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2026-06-30T03:29:21Z","cross_cats_sorted":[],"title_canon_sha256":"c5632f6f050b40611d29c36a3bc539863a63b5e69bb4f8444d0fa9308222a7c2","abstract_canon_sha256":"56c2a89ee182fea2ada0a5a78e0965099e28d006cee3a33558c7ccb35792578d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-01T01:17:28.831143Z","signature_b64":"yEuNKuiXO6qtpMngk8qif5jLKflyJRyyVj0P2mnw7NwHB2Qlkd6eyK6iNVGVWOCehJEj9XEu/SE48sWCN08hCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f765c3359da4c425e1854f5c620f8473f157159651798a85c23ee3b6b112e355","last_reissued_at":"2026-07-01T01:17:28.830741Z","signature_status":"signed_v1","first_computed_at":"2026-07-01T01:17:28.830741Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Omni-Flow: A Unified Workflow Orchestration and Distributed KV Cache Sharing Framework for Multimodal Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DC","authors_text":"Bin Xiao, Changran Wang, Jianping Lin, Jingfu Dong, Xiaoyu Zhao, Yitian Chen, Yuchen Xie, Yuqi Peng","submitted_at":"2026-06-30T03:29:21Z","abstract_excerpt":"As large language model (LLM) inference evolves from text-only to multimodal paradigms, inference systems face three challenges: (1) flexible orchestration of multimodal workflows, where heterogeneous computing units exhibit complex dependencies and concurrent control; (2) efficient transmission of massive intermediate data across processes and nodes, with tensors flowing at high speed among heterogeneous roles; and (3) efficient sharing of KV caches and model weights across roles to eliminate redundant GPU memory. Existing solutions deploy LLMs and diffusion models independently, lacking a sy"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.31093","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2606.31093/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.31093","created_at":"2026-07-01T01:17:28.830796+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.31093v1","created_at":"2026-07-01T01:17:28.830796+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.31093","created_at":"2026-07-01T01:17:28.830796+00:00"},{"alias_kind":"pith_short_12","alias_value":"65S4GNM5UTCC","created_at":"2026-07-01T01:17:28.830796+00:00"},{"alias_kind":"pith_short_16","alias_value":"65S4GNM5UTCCLYMF","created_at":"2026-07-01T01:17:28.830796+00:00"},{"alias_kind":"pith_short_8","alias_value":"65S4GNM5","created_at":"2026-07-01T01:17:28.830796+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/65S4GNM5UTCCLYMFJ5OGED4EOP","json":"https://pith.science/pith/65S4GNM5UTCCLYMFJ5OGED4EOP.json","graph_json":"https://pith.science/api/pith-number/65S4GNM5UTCCLYMFJ5OGED4EOP/graph.json","events_json":"https://pith.science/api/pith-number/65S4GNM5UTCCLYMFJ5OGED4EOP/events.json","paper":"https://pith.science/paper/65S4GNM5"},"agent_actions":{"view_html":"https://pith.science/pith/65S4GNM5UTCCLYMFJ5OGED4EOP","download_json":"https://pith.science/pith/65S4GNM5UTCCLYMFJ5OGED4EOP.json","view_paper":"https://pith.science/paper/65S4GNM5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.31093&json=true","fetch_graph":"https://pith.science/api/pith-number/65S4GNM5UTCCLYMFJ5OGED4EOP/graph.json","fetch_events":"https://pith.science/api/pith-number/65S4GNM5UTCCLYMFJ5OGED4EOP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/65S4GNM5UTCCLYMFJ5OGED4EOP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/65S4GNM5UTCCLYMFJ5OGED4EOP/action/storage_attestation","attest_author":"https://pith.science/pith/65S4GNM5UTCCLYMFJ5OGED4EOP/action/author_attestation","sign_citation":"https://pith.science/pith/65S4GNM5UTCCLYMFJ5OGED4EOP/action/citation_signature","submit_replication":"https://pith.science/pith/65S4GNM5UTCCLYMFJ5OGED4EOP/action/replication_record"}},"created_at":"2026-07-01T01:17:28.830796+00:00","updated_at":"2026-07-01T01:17:28.830796+00:00"}