{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:XMJPGOEHO7JND63A2JHC3VEHTV","short_pith_number":"pith:XMJPGOEH","schema_version":"1.0","canonical_sha256":"bb12f3388777d2d1fb60d24e2dd4879d56899b4795ecf4d059a7c38f5e798027","source":{"kind":"arxiv","id":"2312.15159","version":2},"attestation_state":"computed","paper":{"title":"Understanding the Potential of FPGA-Based Spatial Acceleration for Large Language Model Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.AR","cs.CL"],"primary_cat":"cs.LG","authors_text":"Hongzheng Chen, Jiahao Zhang, Niansong Zhang, Shaojie Xiang, Yaohui Cai, Yixiao Du, Zhiru Zhang, Zichao Yue","submitted_at":"2023-12-23T04:27:06Z","abstract_excerpt":"Recent advancements in large language models (LLMs) boasting billions of parameters have generated a significant demand for efficient deployment in inference workloads. The majority of existing approaches rely on temporal architectures that reuse hardware units for different network layers and operators. However, these methods often encounter challenges in achieving low latency due to considerable memory access overhead. This paper investigates the feasibility and potential of model-specific spatial acceleration for LLM inference on FPGAs. Our approach involves the specialization of distinct h"},"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":"2312.15159","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-12-23T04:27:06Z","cross_cats_sorted":["cs.AI","cs.AR","cs.CL"],"title_canon_sha256":"27bc5ed43bf25209a9422e57923e5191318cb8dba7455add75111409758315f3","abstract_canon_sha256":"f422d86101ea7496c98feb648257ab7156dc7e32128305f7fa8a0882e5b32b45"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:05:07.567869Z","signature_b64":"gskc9g4RIlJbtzE7uYhCxgroSq0XL0Ki6wPdLBrGgsHl3sX40CccDOwRhu8LJzSXZN2QJ+WzxUfzOD8JdJeUBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bb12f3388777d2d1fb60d24e2dd4879d56899b4795ecf4d059a7c38f5e798027","last_reissued_at":"2026-07-05T08:05:07.567393Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:05:07.567393Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Understanding the Potential of FPGA-Based Spatial Acceleration for Large Language Model Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.AR","cs.CL"],"primary_cat":"cs.LG","authors_text":"Hongzheng Chen, Jiahao Zhang, Niansong Zhang, Shaojie Xiang, Yaohui Cai, Yixiao Du, Zhiru Zhang, Zichao Yue","submitted_at":"2023-12-23T04:27:06Z","abstract_excerpt":"Recent advancements in large language models (LLMs) boasting billions of parameters have generated a significant demand for efficient deployment in inference workloads. The majority of existing approaches rely on temporal architectures that reuse hardware units for different network layers and operators. However, these methods often encounter challenges in achieving low latency due to considerable memory access overhead. This paper investigates the feasibility and potential of model-specific spatial acceleration for LLM inference on FPGAs. Our approach involves the specialization of distinct h"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.15159","kind":"arxiv","version":2},"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/2312.15159/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":"2312.15159","created_at":"2026-07-05T08:05:07.567451+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.15159v2","created_at":"2026-07-05T08:05:07.567451+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.15159","created_at":"2026-07-05T08:05:07.567451+00:00"},{"alias_kind":"pith_short_12","alias_value":"XMJPGOEHO7JN","created_at":"2026-07-05T08:05:07.567451+00:00"},{"alias_kind":"pith_short_16","alias_value":"XMJPGOEHO7JND63A","created_at":"2026-07-05T08:05:07.567451+00:00"},{"alias_kind":"pith_short_8","alias_value":"XMJPGOEH","created_at":"2026-07-05T08:05:07.567451+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2404.14294","citing_title":"A Survey on Efficient Inference for Large Language Models","ref_index":294,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XMJPGOEHO7JND63A2JHC3VEHTV","json":"https://pith.science/pith/XMJPGOEHO7JND63A2JHC3VEHTV.json","graph_json":"https://pith.science/api/pith-number/XMJPGOEHO7JND63A2JHC3VEHTV/graph.json","events_json":"https://pith.science/api/pith-number/XMJPGOEHO7JND63A2JHC3VEHTV/events.json","paper":"https://pith.science/paper/XMJPGOEH"},"agent_actions":{"view_html":"https://pith.science/pith/XMJPGOEHO7JND63A2JHC3VEHTV","download_json":"https://pith.science/pith/XMJPGOEHO7JND63A2JHC3VEHTV.json","view_paper":"https://pith.science/paper/XMJPGOEH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.15159&json=true","fetch_graph":"https://pith.science/api/pith-number/XMJPGOEHO7JND63A2JHC3VEHTV/graph.json","fetch_events":"https://pith.science/api/pith-number/XMJPGOEHO7JND63A2JHC3VEHTV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XMJPGOEHO7JND63A2JHC3VEHTV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XMJPGOEHO7JND63A2JHC3VEHTV/action/storage_attestation","attest_author":"https://pith.science/pith/XMJPGOEHO7JND63A2JHC3VEHTV/action/author_attestation","sign_citation":"https://pith.science/pith/XMJPGOEHO7JND63A2JHC3VEHTV/action/citation_signature","submit_replication":"https://pith.science/pith/XMJPGOEHO7JND63A2JHC3VEHTV/action/replication_record"}},"created_at":"2026-07-05T08:05:07.567451+00:00","updated_at":"2026-07-05T08:05:07.567451+00:00"}