{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ONJUYKGNI6UKQ5V62ZBAPLUY7E","short_pith_number":"pith:ONJUYKGN","schema_version":"1.0","canonical_sha256":"73534c28cd47a8a876bed64207ae98f930710275572599caabc3257d8fa3491f","source":{"kind":"arxiv","id":"2505.03745","version":1},"attestation_state":"computed","paper":{"title":"AccLLM: Accelerating Long-Context LLM Inference Via Algorithm-Hardware Co-Design","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.AR","authors_text":"Haikuo Shao, Huihong Shi, Yanbiao Liang, Zhongfeng Wang","submitted_at":"2025-04-07T02:52:30Z","abstract_excerpt":"Recently, large language models (LLMs) have achieved huge success in the natural language processing (NLP) field, driving a growing demand to extend their deployment from the cloud to edge devices. However, deploying LLMs on resource-constrained edge devices poses significant challenges, including (1) intensive computations and huge model sizes, (2) great memory and bandwidth demands introduced by the autoregressive generation process, and (3) limited scalability for handling long sequences. To address these challenges, we propose AccLLM, a comprehensive acceleration framework that enables eff"},"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":"2505.03745","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AR","submitted_at":"2025-04-07T02:52:30Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"545d3a78fe0fa1b00474181a5b10fd6a86d2fe69481edffac21b996d2fb54a64","abstract_canon_sha256":"dd4f325f3f50b461b9f6383877b4c280b7cae6c61d6e12c298f5f5804afdcefc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:59:30.230125Z","signature_b64":"oIFBU2xGnSZGle6IsZegRu1ZB3qyJxRQ/QGnTAkZlteZAhr/k2LuJGtV1AiP/ILbH4CcjWTRmj2grskSIuBlDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"73534c28cd47a8a876bed64207ae98f930710275572599caabc3257d8fa3491f","last_reissued_at":"2026-07-05T10:59:30.229715Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:59:30.229715Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AccLLM: Accelerating Long-Context LLM Inference Via Algorithm-Hardware Co-Design","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.AR","authors_text":"Haikuo Shao, Huihong Shi, Yanbiao Liang, Zhongfeng Wang","submitted_at":"2025-04-07T02:52:30Z","abstract_excerpt":"Recently, large language models (LLMs) have achieved huge success in the natural language processing (NLP) field, driving a growing demand to extend their deployment from the cloud to edge devices. However, deploying LLMs on resource-constrained edge devices poses significant challenges, including (1) intensive computations and huge model sizes, (2) great memory and bandwidth demands introduced by the autoregressive generation process, and (3) limited scalability for handling long sequences. To address these challenges, we propose AccLLM, a comprehensive acceleration framework that enables eff"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.03745","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/2505.03745/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":"2505.03745","created_at":"2026-07-05T10:59:30.229772+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.03745v1","created_at":"2026-07-05T10:59:30.229772+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.03745","created_at":"2026-07-05T10:59:30.229772+00:00"},{"alias_kind":"pith_short_12","alias_value":"ONJUYKGNI6UK","created_at":"2026-07-05T10:59:30.229772+00:00"},{"alias_kind":"pith_short_16","alias_value":"ONJUYKGNI6UKQ5V6","created_at":"2026-07-05T10:59:30.229772+00:00"},{"alias_kind":"pith_short_8","alias_value":"ONJUYKGN","created_at":"2026-07-05T10:59:30.229772+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ONJUYKGNI6UKQ5V62ZBAPLUY7E","json":"https://pith.science/pith/ONJUYKGNI6UKQ5V62ZBAPLUY7E.json","graph_json":"https://pith.science/api/pith-number/ONJUYKGNI6UKQ5V62ZBAPLUY7E/graph.json","events_json":"https://pith.science/api/pith-number/ONJUYKGNI6UKQ5V62ZBAPLUY7E/events.json","paper":"https://pith.science/paper/ONJUYKGN"},"agent_actions":{"view_html":"https://pith.science/pith/ONJUYKGNI6UKQ5V62ZBAPLUY7E","download_json":"https://pith.science/pith/ONJUYKGNI6UKQ5V62ZBAPLUY7E.json","view_paper":"https://pith.science/paper/ONJUYKGN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.03745&json=true","fetch_graph":"https://pith.science/api/pith-number/ONJUYKGNI6UKQ5V62ZBAPLUY7E/graph.json","fetch_events":"https://pith.science/api/pith-number/ONJUYKGNI6UKQ5V62ZBAPLUY7E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ONJUYKGNI6UKQ5V62ZBAPLUY7E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ONJUYKGNI6UKQ5V62ZBAPLUY7E/action/storage_attestation","attest_author":"https://pith.science/pith/ONJUYKGNI6UKQ5V62ZBAPLUY7E/action/author_attestation","sign_citation":"https://pith.science/pith/ONJUYKGNI6UKQ5V62ZBAPLUY7E/action/citation_signature","submit_replication":"https://pith.science/pith/ONJUYKGNI6UKQ5V62ZBAPLUY7E/action/replication_record"}},"created_at":"2026-07-05T10:59:30.229772+00:00","updated_at":"2026-07-05T10:59:30.229772+00:00"}