{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:L2BSKLNG4HZJNAPWVWJMNLME5Y","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":"e8bdab36ca5eca12b9b1ecdcf783750b2b285331f14c6cc59a8dc9647f5f9bcf","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2024-06-03T17:47:53Z","title_canon_sha256":"2c452c7ecf832806ab4fdc4b1e06936c75349ffe07116a88955b0fe2f30b12fa"},"schema_version":"1.0","source":{"id":"2406.01566","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.01566","created_at":"2026-07-05T10:25:07Z"},{"alias_kind":"arxiv_version","alias_value":"2406.01566v2","created_at":"2026-07-05T10:25:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.01566","created_at":"2026-07-05T10:25:07Z"},{"alias_kind":"pith_short_12","alias_value":"L2BSKLNG4HZJ","created_at":"2026-07-05T10:25:07Z"},{"alias_kind":"pith_short_16","alias_value":"L2BSKLNG4HZJNAPW","created_at":"2026-07-05T10:25:07Z"},{"alias_kind":"pith_short_8","alias_value":"L2BSKLNG","created_at":"2026-07-05T10:25:07Z"}],"graph_snapshots":[{"event_id":"sha256:829c573f041270728db7500a1afc76184c40b3801c83eed99f7854fae5059aff","target":"graph","created_at":"2026-07-05T10:25:07Z","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/2406.01566/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper introduces Helix, a distributed system for high-throughput, low-latency large language model (LLM) serving in heterogeneous GPU clusters. The key idea behind Helix is to formulate inference computation of LLMs over heterogeneous GPUs and network connections as a max-flow problem on directed, weighted graphs, whose nodes represent GPU instances and edges capture both GPU and network heterogeneity through their capacities. Helix then uses a mixed integer linear programming (MILP) algorithm to discover highly optimized strategies to serve LLMs on heterogeneous GPUs. This approach allow","authors_text":"Juncheng Yang, Rashmi Vinayak, Xupeng Miao, Yixuan Mei, Yonghao Zhuang, Zhihao Jia","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2024-06-03T17:47:53Z","title":"Helix: Serving Large Language Models over Heterogeneous GPUs and Network via Max-Flow"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.01566","kind":"arxiv","version":2},"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:d28298237937f6488e064f7ef2ff3b5c32f59a11546e5364f2d307416281392f","target":"record","created_at":"2026-07-05T10:25:07Z","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":"e8bdab36ca5eca12b9b1ecdcf783750b2b285331f14c6cc59a8dc9647f5f9bcf","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2024-06-03T17:47:53Z","title_canon_sha256":"2c452c7ecf832806ab4fdc4b1e06936c75349ffe07116a88955b0fe2f30b12fa"},"schema_version":"1.0","source":{"id":"2406.01566","kind":"arxiv","version":2}},"canonical_sha256":"5e83252da6e1f29681f6ad92c6ad84ee34e8d6952e68db33be4f3fa2931ff5cb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5e83252da6e1f29681f6ad92c6ad84ee34e8d6952e68db33be4f3fa2931ff5cb","first_computed_at":"2026-07-05T10:25:07.030177Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:25:07.030177Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kgU7G2kU/89sNG7rMkbTBYV+g0iW9ZEMUPNpcW69szr397RLAStzOOaBKAtJjQB7kkn+iW5IZRO1dQLF4nPDBg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:25:07.030872Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.01566","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d28298237937f6488e064f7ef2ff3b5c32f59a11546e5364f2d307416281392f","sha256:829c573f041270728db7500a1afc76184c40b3801c83eed99f7854fae5059aff"],"state_sha256":"f9e2159f6acab44946fe221925b886d9f7a84b1dce59e7157e830584c16c0fd1"}