{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WKFOJ2ECV52KUJR3SCIBSQ4GYD","short_pith_number":"pith:WKFOJ2EC","schema_version":"1.0","canonical_sha256":"b28ae4e882af74aa263b9090194386c0fbba48f6ff6193e3a004aee35b542495","source":{"kind":"arxiv","id":"2403.01164","version":1},"attestation_state":"computed","paper":{"title":"HeteGen: Heterogeneous Parallel Inference for Large Language Models on Resource-Constrained Devices","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC"],"primary_cat":"cs.PF","authors_text":"Bin Jia, Haotian Zhou, Shenggan Cheng, Xuanlei Zhao, Yang You, Ziming Liu","submitted_at":"2024-03-02T10:37:21Z","abstract_excerpt":"In recent times, the emergence of Large Language Models (LLMs) has resulted in increasingly larger model size, posing challenges for inference on low-resource devices. Prior approaches have explored offloading to facilitate low-memory inference but often suffer from efficiency due to I/O bottlenecks. To achieve low-latency LLMs inference on resource-constrained devices, we introduce HeteGen, a novel approach that presents a principled framework for heterogeneous parallel computing using CPUs and GPUs. Based on this framework, HeteGen further employs heterogeneous parallel computing and asynchr"},"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":"2403.01164","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.PF","submitted_at":"2024-03-02T10:37:21Z","cross_cats_sorted":["cs.DC"],"title_canon_sha256":"21ba88e563214b68a464ad3ae0b7ec819c8c01f3bdd823e6161344f138d7288c","abstract_canon_sha256":"fdb37718ac307ae4fd46c3fe3c2b432eeb177dd243d4feed7e569cb246aea2cd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:51:43.241582Z","signature_b64":"uHdk7TLPbR5wpCZM4udeo+fgn2haRqv573qL0aRW7ZfoYHA+kL3PLhgW+oSvueItEikCllwmdtjlkzS9ZNtHDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b28ae4e882af74aa263b9090194386c0fbba48f6ff6193e3a004aee35b542495","last_reissued_at":"2026-07-05T07:51:43.241183Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:51:43.241183Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HeteGen: Heterogeneous Parallel Inference for Large Language Models on Resource-Constrained Devices","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC"],"primary_cat":"cs.PF","authors_text":"Bin Jia, Haotian Zhou, Shenggan Cheng, Xuanlei Zhao, Yang You, Ziming Liu","submitted_at":"2024-03-02T10:37:21Z","abstract_excerpt":"In recent times, the emergence of Large Language Models (LLMs) has resulted in increasingly larger model size, posing challenges for inference on low-resource devices. Prior approaches have explored offloading to facilitate low-memory inference but often suffer from efficiency due to I/O bottlenecks. To achieve low-latency LLMs inference on resource-constrained devices, we introduce HeteGen, a novel approach that presents a principled framework for heterogeneous parallel computing using CPUs and GPUs. Based on this framework, HeteGen further employs heterogeneous parallel computing and asynchr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.01164","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/2403.01164/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":"2403.01164","created_at":"2026-07-05T07:51:43.241238+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.01164v1","created_at":"2026-07-05T07:51:43.241238+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.01164","created_at":"2026-07-05T07:51:43.241238+00:00"},{"alias_kind":"pith_short_12","alias_value":"WKFOJ2ECV52K","created_at":"2026-07-05T07:51:43.241238+00:00"},{"alias_kind":"pith_short_16","alias_value":"WKFOJ2ECV52KUJR3","created_at":"2026-07-05T07:51:43.241238+00:00"},{"alias_kind":"pith_short_8","alias_value":"WKFOJ2EC","created_at":"2026-07-05T07:51:43.241238+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2601.20309","citing_title":"SuperInfer: SLO-Aware Rotary Scheduling and Memory Management for LLM Inference on Superchips","ref_index":25,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WKFOJ2ECV52KUJR3SCIBSQ4GYD","json":"https://pith.science/pith/WKFOJ2ECV52KUJR3SCIBSQ4GYD.json","graph_json":"https://pith.science/api/pith-number/WKFOJ2ECV52KUJR3SCIBSQ4GYD/graph.json","events_json":"https://pith.science/api/pith-number/WKFOJ2ECV52KUJR3SCIBSQ4GYD/events.json","paper":"https://pith.science/paper/WKFOJ2EC"},"agent_actions":{"view_html":"https://pith.science/pith/WKFOJ2ECV52KUJR3SCIBSQ4GYD","download_json":"https://pith.science/pith/WKFOJ2ECV52KUJR3SCIBSQ4GYD.json","view_paper":"https://pith.science/paper/WKFOJ2EC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.01164&json=true","fetch_graph":"https://pith.science/api/pith-number/WKFOJ2ECV52KUJR3SCIBSQ4GYD/graph.json","fetch_events":"https://pith.science/api/pith-number/WKFOJ2ECV52KUJR3SCIBSQ4GYD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WKFOJ2ECV52KUJR3SCIBSQ4GYD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WKFOJ2ECV52KUJR3SCIBSQ4GYD/action/storage_attestation","attest_author":"https://pith.science/pith/WKFOJ2ECV52KUJR3SCIBSQ4GYD/action/author_attestation","sign_citation":"https://pith.science/pith/WKFOJ2ECV52KUJR3SCIBSQ4GYD/action/citation_signature","submit_replication":"https://pith.science/pith/WKFOJ2ECV52KUJR3SCIBSQ4GYD/action/replication_record"}},"created_at":"2026-07-05T07:51:43.241238+00:00","updated_at":"2026-07-05T07:51:43.241238+00:00"}