{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:B4LVT5T6A2VJIHNGHCUVJPHITY","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"9f6c6ab74ab3a9d3282d38df67cc3095d4e1fb5910e9096775070a9fb6cdbf18","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-03T06:37:50Z","title_canon_sha256":"f5db40cc81e063ac2babfd1d1cd0c3b629f6e0f717b75bd50bfd580da6203c22"},"schema_version":"1.0","source":{"id":"2402.02057","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.02057","created_at":"2026-07-05T07:41:10Z"},{"alias_kind":"arxiv_version","alias_value":"2402.02057v1","created_at":"2026-07-05T07:41:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.02057","created_at":"2026-07-05T07:41:10Z"},{"alias_kind":"pith_short_12","alias_value":"B4LVT5T6A2VJ","created_at":"2026-07-05T07:41:10Z"},{"alias_kind":"pith_short_16","alias_value":"B4LVT5T6A2VJIHNG","created_at":"2026-07-05T07:41:10Z"},{"alias_kind":"pith_short_8","alias_value":"B4LVT5T6","created_at":"2026-07-05T07:41:10Z"}],"graph_snapshots":[{"event_id":"sha256:6ac25531f650421faffb2e9280861de560cafb9d6374344fdc698902f6867b01","target":"graph","created_at":"2026-07-05T07:41:10Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2402.02057/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Autoregressive decoding of large language models (LLMs) is memory bandwidth bounded, resulting in high latency and significant wastes of the parallel processing power of modern accelerators. Existing methods for accelerating LLM decoding often require a draft model (e.g., speculative decoding), which is nontrivial to obtain and unable to generalize. In this paper, we introduce Lookahead decoding, an exact, parallel decoding algorithm that accelerates LLM decoding without needing auxiliary models or data stores. It allows trading per-step log(FLOPs) to reduce the number of total decoding steps,","authors_text":"Hao Zhang, Ion Stoica, Peter Bailis, Yichao Fu","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-03T06:37:50Z","title":"Break the Sequential Dependency of LLM Inference Using Lookahead Decoding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.02057","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:af956a822cce1b96b26d480f168a8c09ea9065aaef377ab58ad3ebeb16db3106","target":"record","created_at":"2026-07-05T07:41:10Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"9f6c6ab74ab3a9d3282d38df67cc3095d4e1fb5910e9096775070a9fb6cdbf18","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-03T06:37:50Z","title_canon_sha256":"f5db40cc81e063ac2babfd1d1cd0c3b629f6e0f717b75bd50bfd580da6203c22"},"schema_version":"1.0","source":{"id":"2402.02057","kind":"arxiv","version":1}},"canonical_sha256":"0f1759f67e06aa941da638a954bce89e2c479c48027367c8109d37f93e17f3b3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0f1759f67e06aa941da638a954bce89e2c479c48027367c8109d37f93e17f3b3","first_computed_at":"2026-07-05T07:41:10.322810Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:41:10.322810Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TeH8C0MMAe6C6VgFJAiDrmI+3ax8mXRwW5uhOJsAGTlnvzLyEt4Vu5QdTPBnPj4c6SZXD3Xiu1bn1LNy6WpRCA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:41:10.323260Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.02057","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:af956a822cce1b96b26d480f168a8c09ea9065aaef377ab58ad3ebeb16db3106","sha256:6ac25531f650421faffb2e9280861de560cafb9d6374344fdc698902f6867b01"],"state_sha256":"790331d659b4a0ef47a65fc39a12651b518c6f2db98452f8ca9cb9db25fe4084"}