{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:RTVKB3YDI5EP37MBYCUZDJBJAE","short_pith_number":"pith:RTVKB3YD","schema_version":"1.0","canonical_sha256":"8ceaa0ef034748fdfd81c0a991a429013d163e0fc70df380cdafb38d42612d23","source":{"kind":"arxiv","id":"2409.03384","version":1},"attestation_state":"computed","paper":{"title":"Hardware Acceleration of LLMs: A comprehensive survey and comparison","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.AR","authors_text":"Christoforos Kachris, Nikoletta Koilia","submitted_at":"2024-09-05T09:43:25Z","abstract_excerpt":"Large Language Models (LLMs) have emerged as powerful tools for natural language processing tasks, revolutionizing the field with their ability to understand and generate human-like text. In this paper, we present a comprehensive survey of the several research efforts that have been presented for the acceleration of transformer networks for Large Language Models using hardware accelerators.\n  The survey presents the frameworks that have been proposed and then performs a qualitative and quantitative comparison regarding the technology, the processing platform (FPGA, ASIC, In-Memory, GPU), the 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":"2409.03384","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AR","submitted_at":"2024-09-05T09:43:25Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"324e14dfb915a1a844a825e7d2b1d85863d869db188ed738e18a1be14f420161","abstract_canon_sha256":"a2d19b72f54179d1c6c5aade60907ccb3acadbb3e06c5aedebf414725e944ca3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:03:30.509829Z","signature_b64":"qtFhpA8fUFV7S+ldx0461Z9K1T0rjKm4Cn/Z45vEqagMxKpF0vfClFALeK0wACxeHPifrITr0436WqdO+7jMAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8ceaa0ef034748fdfd81c0a991a429013d163e0fc70df380cdafb38d42612d23","last_reissued_at":"2026-07-05T09:03:30.509270Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:03:30.509270Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hardware Acceleration of LLMs: A comprehensive survey and comparison","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.AR","authors_text":"Christoforos Kachris, Nikoletta Koilia","submitted_at":"2024-09-05T09:43:25Z","abstract_excerpt":"Large Language Models (LLMs) have emerged as powerful tools for natural language processing tasks, revolutionizing the field with their ability to understand and generate human-like text. In this paper, we present a comprehensive survey of the several research efforts that have been presented for the acceleration of transformer networks for Large Language Models using hardware accelerators.\n  The survey presents the frameworks that have been proposed and then performs a qualitative and quantitative comparison regarding the technology, the processing platform (FPGA, ASIC, In-Memory, GPU), the s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.03384","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/2409.03384/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":"2409.03384","created_at":"2026-07-05T09:03:30.509341+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.03384v1","created_at":"2026-07-05T09:03:30.509341+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.03384","created_at":"2026-07-05T09:03:30.509341+00:00"},{"alias_kind":"pith_short_12","alias_value":"RTVKB3YDI5EP","created_at":"2026-07-05T09:03:30.509341+00:00"},{"alias_kind":"pith_short_16","alias_value":"RTVKB3YDI5EP37MB","created_at":"2026-07-05T09:03:30.509341+00:00"},{"alias_kind":"pith_short_8","alias_value":"RTVKB3YD","created_at":"2026-07-05T09:03:30.509341+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.22935","citing_title":"Secure eFPGA-Enabled Edge LLM Inference: Architectural and Hardware Countermeasures","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04178","citing_title":"Microbenchmark-Driven Analytical Performance Modeling Across Modern GPU Architectures","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RTVKB3YDI5EP37MBYCUZDJBJAE","json":"https://pith.science/pith/RTVKB3YDI5EP37MBYCUZDJBJAE.json","graph_json":"https://pith.science/api/pith-number/RTVKB3YDI5EP37MBYCUZDJBJAE/graph.json","events_json":"https://pith.science/api/pith-number/RTVKB3YDI5EP37MBYCUZDJBJAE/events.json","paper":"https://pith.science/paper/RTVKB3YD"},"agent_actions":{"view_html":"https://pith.science/pith/RTVKB3YDI5EP37MBYCUZDJBJAE","download_json":"https://pith.science/pith/RTVKB3YDI5EP37MBYCUZDJBJAE.json","view_paper":"https://pith.science/paper/RTVKB3YD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.03384&json=true","fetch_graph":"https://pith.science/api/pith-number/RTVKB3YDI5EP37MBYCUZDJBJAE/graph.json","fetch_events":"https://pith.science/api/pith-number/RTVKB3YDI5EP37MBYCUZDJBJAE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RTVKB3YDI5EP37MBYCUZDJBJAE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RTVKB3YDI5EP37MBYCUZDJBJAE/action/storage_attestation","attest_author":"https://pith.science/pith/RTVKB3YDI5EP37MBYCUZDJBJAE/action/author_attestation","sign_citation":"https://pith.science/pith/RTVKB3YDI5EP37MBYCUZDJBJAE/action/citation_signature","submit_replication":"https://pith.science/pith/RTVKB3YDI5EP37MBYCUZDJBJAE/action/replication_record"}},"created_at":"2026-07-05T09:03:30.509341+00:00","updated_at":"2026-07-05T09:03:30.509341+00:00"}