{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:7YITP32NGRHKOREGDUHGQCHOYD","short_pith_number":"pith:7YITP32N","schema_version":"1.0","canonical_sha256":"fe1137ef4d344ea744861d0e6808eec0f91434d9047a463a5e9a1ef6dbd71203","source":{"kind":"arxiv","id":"2407.07304","version":1},"attestation_state":"computed","paper":{"title":"Inference Performance Optimization for Large Language Models on CPUs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Bin Guo, Changqing Li, Chen Meng, Duyi Wang, Pujiang He, Shan Zhou, Sheng Gui, Weifei Yu, Wenhuan Huang, Yi Xie","submitted_at":"2024-07-10T01:53:49Z","abstract_excerpt":"Large language models (LLMs) have shown exceptional performance and vast potential across diverse tasks. However, the deployment of LLMs with high performance in low-resource environments has garnered significant attention in the industry. When GPU hardware resources are limited, we can explore alternative options on CPUs. To mitigate the financial burden and alleviate constraints imposed by hardware resources, optimizing inference performance is necessary. In this paper, we introduce an easily deployable inference performance optimization solution aimed at accelerating LLMs on CPUs. In this s"},"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":"2407.07304","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-07-10T01:53:49Z","cross_cats_sorted":[],"title_canon_sha256":"2e24f9cccc4aa313abd8781e252b2a115ab5ecaaca69be4a56a6a7c2a542ee45","abstract_canon_sha256":"833d5e8a07660217f966904414acce9d09ae731566ee32019add5844736e3f41"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:42:09.586858Z","signature_b64":"6tHsu1npoq9jBlcx8DUKw1G4hsqwyBFpzhLcXLy1CmhGqh+RD9iPtckdhGOrInjUa80JR+fJQvpJEBZ4BReRBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fe1137ef4d344ea744861d0e6808eec0f91434d9047a463a5e9a1ef6dbd71203","last_reissued_at":"2026-07-05T08:42:09.586459Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:42:09.586459Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Inference Performance Optimization for Large Language Models on CPUs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Bin Guo, Changqing Li, Chen Meng, Duyi Wang, Pujiang He, Shan Zhou, Sheng Gui, Weifei Yu, Wenhuan Huang, Yi Xie","submitted_at":"2024-07-10T01:53:49Z","abstract_excerpt":"Large language models (LLMs) have shown exceptional performance and vast potential across diverse tasks. However, the deployment of LLMs with high performance in low-resource environments has garnered significant attention in the industry. When GPU hardware resources are limited, we can explore alternative options on CPUs. To mitigate the financial burden and alleviate constraints imposed by hardware resources, optimizing inference performance is necessary. In this paper, we introduce an easily deployable inference performance optimization solution aimed at accelerating LLMs on CPUs. In this s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.07304","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/2407.07304/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":"2407.07304","created_at":"2026-07-05T08:42:09.586513+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.07304v1","created_at":"2026-07-05T08:42:09.586513+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.07304","created_at":"2026-07-05T08:42:09.586513+00:00"},{"alias_kind":"pith_short_12","alias_value":"7YITP32NGRHK","created_at":"2026-07-05T08:42:09.586513+00:00"},{"alias_kind":"pith_short_16","alias_value":"7YITP32NGRHKOREG","created_at":"2026-07-05T08:42:09.586513+00:00"},{"alias_kind":"pith_short_8","alias_value":"7YITP32N","created_at":"2026-07-05T08:42:09.586513+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.11948","citing_title":"Active Imitation Learning for Thermal- and Kernel-Aware LFM Inference on 3D S-NUCA Many-Cores","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7YITP32NGRHKOREGDUHGQCHOYD","json":"https://pith.science/pith/7YITP32NGRHKOREGDUHGQCHOYD.json","graph_json":"https://pith.science/api/pith-number/7YITP32NGRHKOREGDUHGQCHOYD/graph.json","events_json":"https://pith.science/api/pith-number/7YITP32NGRHKOREGDUHGQCHOYD/events.json","paper":"https://pith.science/paper/7YITP32N"},"agent_actions":{"view_html":"https://pith.science/pith/7YITP32NGRHKOREGDUHGQCHOYD","download_json":"https://pith.science/pith/7YITP32NGRHKOREGDUHGQCHOYD.json","view_paper":"https://pith.science/paper/7YITP32N","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.07304&json=true","fetch_graph":"https://pith.science/api/pith-number/7YITP32NGRHKOREGDUHGQCHOYD/graph.json","fetch_events":"https://pith.science/api/pith-number/7YITP32NGRHKOREGDUHGQCHOYD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7YITP32NGRHKOREGDUHGQCHOYD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7YITP32NGRHKOREGDUHGQCHOYD/action/storage_attestation","attest_author":"https://pith.science/pith/7YITP32NGRHKOREGDUHGQCHOYD/action/author_attestation","sign_citation":"https://pith.science/pith/7YITP32NGRHKOREGDUHGQCHOYD/action/citation_signature","submit_replication":"https://pith.science/pith/7YITP32NGRHKOREGDUHGQCHOYD/action/replication_record"}},"created_at":"2026-07-05T08:42:09.586513+00:00","updated_at":"2026-07-05T08:42:09.586513+00:00"}