{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:4HT3Q46XOBKAPZZHJBA2ZOWJZ4","short_pith_number":"pith:4HT3Q46X","schema_version":"1.0","canonical_sha256":"e1e7b873d7705407e7274841acbac9cf35dc7ad4a60bb028b6753d9d4fd70f87","source":{"kind":"arxiv","id":"2605.13784","version":1},"attestation_state":"computed","paper":{"title":"Attention Once Is All You Need: Efficient Streaming Inference with Stateful Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Stateful sessions with persistent KV caches let streaming transformer queries run in time independent of context size.","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Victor Norgren","submitted_at":"2026-05-13T17:06:15Z","abstract_excerpt":"Conventional transformer inference engines are request-driven, paying an O(n) prefill cost on every query. In streaming workloads, where data arrives continuously and queries probe an ever-growing context, this cost is prohibitive. We introduce a data-driven computational model centred on stateful sessions: a persistent KV cache advanced incrementally as new data arrives, so prefill is moved off the critical path and query latency becomes O(|q|), independent of accumulated context size. Building on this, Flash Queries reclaim idle GPU cycles between data arrivals to pre-evaluate registered que"},"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":true,"formal_links_present":false},"canonical_record":{"source":{"id":"2605.13784","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-13T17:06:15Z","cross_cats_sorted":[],"title_canon_sha256":"c02974716d1ef298f9e1780a9054c448f6d79e4fd29987f4ce8faa7df932c10d","abstract_canon_sha256":"bd29f8c25355fee4f2d5f38a0228802a52c9dc460029c06a1cb59b935799d4dc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:44:15.704191Z","signature_b64":"L9BxDxHKHnNaS6pG2CGPcogPB6Mgk/97YB9ezsg0lEE3FPmTIWykrzS20tEIYXZWsF2zpRoCFqplBaSAUVSJDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e1e7b873d7705407e7274841acbac9cf35dc7ad4a60bb028b6753d9d4fd70f87","last_reissued_at":"2026-05-18T02:44:15.703620Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:44:15.703620Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Attention Once Is All You Need: Efficient Streaming Inference with Stateful Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Stateful sessions with persistent KV caches let streaming transformer queries run in time independent of context size.","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Victor Norgren","submitted_at":"2026-05-13T17:06:15Z","abstract_excerpt":"Conventional transformer inference engines are request-driven, paying an O(n) prefill cost on every query. In streaming workloads, where data arrives continuously and queries probe an ever-growing context, this cost is prohibitive. We introduce a data-driven computational model centred on stateful sessions: a persistent KV cache advanced incrementally as new data arrives, so prefill is moved off the critical path and query latency becomes O(|q|), independent of accumulated context size. Building on this, Flash Queries reclaim idle GPU cycles between data arrivals to pre-evaluate registered que"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"On streaming market-data benchmarks the reference implementation achieves up to 5.9x speedup over conventional inference engines (vLLM, SGLang, TensorRT-LLM, llama.cpp), holding query latency constant as accumulated context grows.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That a multi-tenant continuous-batching scheduler with cell-budget admission and prefix-aware grouped prefill can maintain full quadratic self-attention across dozens of stateful sessions without correctness loss or prohibitive overhead.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Stateful sessions with incremental KV cache and flash queries allow O(|q|) latency in streaming transformer inference, delivering up to 5.9x speedup over conventional engines while preserving full attention.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Stateful sessions with persistent KV caches let streaming transformer queries run in time independent of context size.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"207dd651ac10f9a3c9b729cc7b456f8ba4fe592ec44a60c35d50ea43a45c49ba"},"source":{"id":"2605.13784","kind":"arxiv","version":1},"verdict":{"id":"381654ce-1b87-4538-bc9b-f0672729f336","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T19:16:51.175879Z","strongest_claim":"On streaming market-data benchmarks the reference implementation achieves up to 5.9x speedup over conventional inference engines (vLLM, SGLang, TensorRT-LLM, llama.cpp), holding query latency constant as accumulated context grows.","one_line_summary":"Stateful sessions with incremental KV cache and flash queries allow O(|q|) latency in streaming transformer inference, delivering up to 5.9x speedup over conventional engines while preserving full attention.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That a multi-tenant continuous-batching scheduler with cell-budget admission and prefix-aware grouped prefill can maintain full quadratic self-attention across dozens of stateful sessions without correctness loss or prohibitive overhead.","pith_extraction_headline":"Stateful sessions with persistent KV caches let streaming transformer queries run in time independent of context size."},"references":{"count":20,"sample":[{"doi":"","year":2023,"title":"Lopez-Lira, A. and Tang, Y. Can ChatGPT Forecast Stock Price Movements? Return Predictability and Large Language Models. SSRN, 2023","work_id":"7e8454c1-04ca-4350-8143-7510902ea219","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"BloombergGPT: A Large Language Model for Finance","work_id":"04e9adc6-bece-4ff4-a0f6-e836d88414a7","ref_index":2,"cited_arxiv_id":"2303.17564","is_internal_anchor":true},{"doi":"","year":2024,"title":"Lost in the Middle: How Language Models Use Long Contexts","work_id":"1616dd1e-4de8-4717-a816-b131cad65926","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"Prompt Caching","work_id":"278a7fa4-e0b4-4ec6-9bc3-fe1ff8995197","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2004,"title":"Longformer: The Long-Document Transformer","work_id":"abea7a44-6668-4de7-aab6-f53a6e5aa088","ref_index":5,"cited_arxiv_id":"2004.05150","is_internal_anchor":true}],"resolved_work":20,"snapshot_sha256":"75e2bae35ff0b2d4f867ea960d54ddc78285ef194f5d5e5f29272cacaff5755d","internal_anchors":8},"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":"2605.13784","created_at":"2026-05-18T02:44:15.703708+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.13784v1","created_at":"2026-05-18T02:44:15.703708+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13784","created_at":"2026-05-18T02:44:15.703708+00:00"},{"alias_kind":"pith_short_12","alias_value":"4HT3Q46XOBKA","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"4HT3Q46XOBKAPZZH","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"4HT3Q46X","created_at":"2026-05-18T12:33:37.589309+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/4HT3Q46XOBKAPZZHJBA2ZOWJZ4","json":"https://pith.science/pith/4HT3Q46XOBKAPZZHJBA2ZOWJZ4.json","graph_json":"https://pith.science/api/pith-number/4HT3Q46XOBKAPZZHJBA2ZOWJZ4/graph.json","events_json":"https://pith.science/api/pith-number/4HT3Q46XOBKAPZZHJBA2ZOWJZ4/events.json","paper":"https://pith.science/paper/4HT3Q46X"},"agent_actions":{"view_html":"https://pith.science/pith/4HT3Q46XOBKAPZZHJBA2ZOWJZ4","download_json":"https://pith.science/pith/4HT3Q46XOBKAPZZHJBA2ZOWJZ4.json","view_paper":"https://pith.science/paper/4HT3Q46X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.13784&json=true","fetch_graph":"https://pith.science/api/pith-number/4HT3Q46XOBKAPZZHJBA2ZOWJZ4/graph.json","fetch_events":"https://pith.science/api/pith-number/4HT3Q46XOBKAPZZHJBA2ZOWJZ4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4HT3Q46XOBKAPZZHJBA2ZOWJZ4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4HT3Q46XOBKAPZZHJBA2ZOWJZ4/action/storage_attestation","attest_author":"https://pith.science/pith/4HT3Q46XOBKAPZZHJBA2ZOWJZ4/action/author_attestation","sign_citation":"https://pith.science/pith/4HT3Q46XOBKAPZZHJBA2ZOWJZ4/action/citation_signature","submit_replication":"https://pith.science/pith/4HT3Q46XOBKAPZZHJBA2ZOWJZ4/action/replication_record"}},"created_at":"2026-05-18T02:44:15.703708+00:00","updated_at":"2026-05-18T02:44:15.703708+00:00"}