{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:WKFOJ2ECV52KUJR3SCIBSQ4GYD","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":"fdb37718ac307ae4fd46c3fe3c2b432eeb177dd243d4feed7e569cb246aea2cd","cross_cats_sorted":["cs.DC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.PF","submitted_at":"2024-03-02T10:37:21Z","title_canon_sha256":"21ba88e563214b68a464ad3ae0b7ec819c8c01f3bdd823e6161344f138d7288c"},"schema_version":"1.0","source":{"id":"2403.01164","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.01164","created_at":"2026-07-05T07:51:43Z"},{"alias_kind":"arxiv_version","alias_value":"2403.01164v1","created_at":"2026-07-05T07:51:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.01164","created_at":"2026-07-05T07:51:43Z"},{"alias_kind":"pith_short_12","alias_value":"WKFOJ2ECV52K","created_at":"2026-07-05T07:51:43Z"},{"alias_kind":"pith_short_16","alias_value":"WKFOJ2ECV52KUJR3","created_at":"2026-07-05T07:51:43Z"},{"alias_kind":"pith_short_8","alias_value":"WKFOJ2EC","created_at":"2026-07-05T07:51:43Z"}],"graph_snapshots":[{"event_id":"sha256:a35884d874d0c4840a8737282cbbaf5be2f4b45477d15483bad6ebc8f8171dae","target":"graph","created_at":"2026-07-05T07:51:43Z","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/2403.01164/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Bin Jia, Haotian Zhou, Shenggan Cheng, Xuanlei Zhao, Yang You, Ziming Liu","cross_cats":["cs.DC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.PF","submitted_at":"2024-03-02T10:37:21Z","title":"HeteGen: Heterogeneous Parallel Inference for Large Language Models on Resource-Constrained Devices"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.01164","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":"sha256:4b91ee9a3893f8afd84b3bd0aa3169499dcad71975f14922aa486e47dd9699f3","target":"record","created_at":"2026-07-05T07:51:43Z","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":"fdb37718ac307ae4fd46c3fe3c2b432eeb177dd243d4feed7e569cb246aea2cd","cross_cats_sorted":["cs.DC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.PF","submitted_at":"2024-03-02T10:37:21Z","title_canon_sha256":"21ba88e563214b68a464ad3ae0b7ec819c8c01f3bdd823e6161344f138d7288c"},"schema_version":"1.0","source":{"id":"2403.01164","kind":"arxiv","version":1}},"canonical_sha256":"b28ae4e882af74aa263b9090194386c0fbba48f6ff6193e3a004aee35b542495","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b28ae4e882af74aa263b9090194386c0fbba48f6ff6193e3a004aee35b542495","first_computed_at":"2026-07-05T07:51:43.241183Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:51:43.241183Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uHdk7TLPbR5wpCZM4udeo+fgn2haRqv573qL0aRW7ZfoYHA+kL3PLhgW+oSvueItEikCllwmdtjlkzS9ZNtHDg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:51:43.241582Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.01164","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4b91ee9a3893f8afd84b3bd0aa3169499dcad71975f14922aa486e47dd9699f3","sha256:a35884d874d0c4840a8737282cbbaf5be2f4b45477d15483bad6ebc8f8171dae"],"state_sha256":"24aa7b76d02d8256e5807ac2205868296290f1c636c718ae29664af29b0b06a5"}