{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:HZ5ULMS2X36YGYINFSN7IZ2G5P","short_pith_number":"pith:HZ5ULMS2","schema_version":"1.0","canonical_sha256":"3e7b45b25abefd83610d2c9bf46746ebe825ec01f7c731aa32f1f0f60ef75404","source":{"kind":"arxiv","id":"2311.11514","version":3},"attestation_state":"computed","paper":{"title":"HexGen: Generative Inference of Large Language Model over Heterogeneous Environment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DC","authors_text":"Beidi Chen, Binhang Yuan, Ran Yan, Xiaozhe Yao, Yang Zhou, Youhe Jiang","submitted_at":"2023-11-20T03:28:57Z","abstract_excerpt":"Serving generative inference of the large language model is a crucial component of contemporary AI applications. This paper focuses on deploying such services in a heterogeneous and cross-datacenter setting to mitigate the substantial inference costs typically associated with a single centralized datacenter. Towards this end, we propose HexGen, a flexible distributed inference engine that uniquely supports the asymmetric partition of generative inference computations over both tensor model parallelism and pipeline parallelism and allows for effective deployment across diverse GPUs interconnect"},"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":"2311.11514","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2023-11-20T03:28:57Z","cross_cats_sorted":[],"title_canon_sha256":"a1b0ed6027edb2f719d00cb8f911cd1e99d8ed71b55e99e1dd9f0b64406efec1","abstract_canon_sha256":"a16fa01c923ac6906e2cd8a26bc484034f63bb665dfa63fef13ff66b7bec3eb9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:23:13.722781Z","signature_b64":"FJ/UFtRtlqipC9ABYo7Jqf3Uyaemd79Lq0UAfO7Ghch96HldmWxefG2bSMZXNwwbK/MJSwNDYcPNkA1fxhKoBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3e7b45b25abefd83610d2c9bf46746ebe825ec01f7c731aa32f1f0f60ef75404","last_reissued_at":"2026-07-05T08:23:13.722312Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:23:13.722312Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HexGen: Generative Inference of Large Language Model over Heterogeneous Environment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DC","authors_text":"Beidi Chen, Binhang Yuan, Ran Yan, Xiaozhe Yao, Yang Zhou, Youhe Jiang","submitted_at":"2023-11-20T03:28:57Z","abstract_excerpt":"Serving generative inference of the large language model is a crucial component of contemporary AI applications. This paper focuses on deploying such services in a heterogeneous and cross-datacenter setting to mitigate the substantial inference costs typically associated with a single centralized datacenter. Towards this end, we propose HexGen, a flexible distributed inference engine that uniquely supports the asymmetric partition of generative inference computations over both tensor model parallelism and pipeline parallelism and allows for effective deployment across diverse GPUs interconnect"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.11514","kind":"arxiv","version":3},"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/2311.11514/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":"2311.11514","created_at":"2026-07-05T08:23:13.722378+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.11514v3","created_at":"2026-07-05T08:23:13.722378+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.11514","created_at":"2026-07-05T08:23:13.722378+00:00"},{"alias_kind":"pith_short_12","alias_value":"HZ5ULMS2X36Y","created_at":"2026-07-05T08:23:13.722378+00:00"},{"alias_kind":"pith_short_16","alias_value":"HZ5ULMS2X36YGYIN","created_at":"2026-07-05T08:23:13.722378+00:00"},{"alias_kind":"pith_short_8","alias_value":"HZ5ULMS2","created_at":"2026-07-05T08:23:13.722378+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.19271","citing_title":"TurboServe: Serving Streaming Video Generation Efficiently and Economically","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16637","citing_title":"HexAGenT: Efficient Agentic LLM Serving via Workflow- and Heterogeneity-Aware Scheduling","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07569","citing_title":"HexiSeq: Accommodating Long Context Training of LLMs over Heterogeneous Hardware","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05227","citing_title":"Rethinking Data Curation in LLM Training: Online Reweighting Offers Better Generalization than Offline Methods","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HZ5ULMS2X36YGYINFSN7IZ2G5P","json":"https://pith.science/pith/HZ5ULMS2X36YGYINFSN7IZ2G5P.json","graph_json":"https://pith.science/api/pith-number/HZ5ULMS2X36YGYINFSN7IZ2G5P/graph.json","events_json":"https://pith.science/api/pith-number/HZ5ULMS2X36YGYINFSN7IZ2G5P/events.json","paper":"https://pith.science/paper/HZ5ULMS2"},"agent_actions":{"view_html":"https://pith.science/pith/HZ5ULMS2X36YGYINFSN7IZ2G5P","download_json":"https://pith.science/pith/HZ5ULMS2X36YGYINFSN7IZ2G5P.json","view_paper":"https://pith.science/paper/HZ5ULMS2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.11514&json=true","fetch_graph":"https://pith.science/api/pith-number/HZ5ULMS2X36YGYINFSN7IZ2G5P/graph.json","fetch_events":"https://pith.science/api/pith-number/HZ5ULMS2X36YGYINFSN7IZ2G5P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HZ5ULMS2X36YGYINFSN7IZ2G5P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HZ5ULMS2X36YGYINFSN7IZ2G5P/action/storage_attestation","attest_author":"https://pith.science/pith/HZ5ULMS2X36YGYINFSN7IZ2G5P/action/author_attestation","sign_citation":"https://pith.science/pith/HZ5ULMS2X36YGYINFSN7IZ2G5P/action/citation_signature","submit_replication":"https://pith.science/pith/HZ5ULMS2X36YGYINFSN7IZ2G5P/action/replication_record"}},"created_at":"2026-07-05T08:23:13.722378+00:00","updated_at":"2026-07-05T08:23:13.722378+00:00"}