{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ZOZN4RW4KFQWLHZUGIBLX747NF","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":"e6b24c461e59acfa7afdc9bfc5b2953a921524d725338a2995517ffd71767215","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-17T08:59:46Z","title_canon_sha256":"e8acc1c3805dde83c83423834019c2bce6865718e62f3bd5d6eb160b1bc7936f"},"schema_version":"1.0","source":{"id":"2405.10637","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.10637","created_at":"2026-07-05T08:26:44Z"},{"alias_kind":"arxiv_version","alias_value":"2405.10637v2","created_at":"2026-07-05T08:26:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.10637","created_at":"2026-07-05T08:26:44Z"},{"alias_kind":"pith_short_12","alias_value":"ZOZN4RW4KFQW","created_at":"2026-07-05T08:26:44Z"},{"alias_kind":"pith_short_16","alias_value":"ZOZN4RW4KFQWLHZU","created_at":"2026-07-05T08:26:44Z"},{"alias_kind":"pith_short_8","alias_value":"ZOZN4RW4","created_at":"2026-07-05T08:26:44Z"}],"graph_snapshots":[{"event_id":"sha256:5bc2bc4a5383b22493837590e10db30a9e6f511d47f7db614f75a6fba7e2468c","target":"graph","created_at":"2026-07-05T08:26:44Z","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/2405.10637/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Huge memory consumption has been a major bottleneck for deploying high-throughput large language models in real-world applications. In addition to the large number of parameters, the key-value (KV) cache for the attention mechanism in the transformer architecture consumes a significant amount of memory, especially when the number of layers is large for deep language models. In this paper, we propose a novel method that only computes and caches the KVs of a small number of layers, thus significantly saving memory consumption and improving inference throughput. Our experiments on large language ","authors_text":"Haoyi Wu, Kewei Tu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-17T08:59:46Z","title":"Layer-Condensed KV Cache for Efficient Inference of Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.10637","kind":"arxiv","version":2},"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":"sha256:74f544ea25a10b9701f846fc20afc68bf0b8917683bf44f115e183f1f0d1ab70","target":"record","created_at":"2026-07-05T08:26:44Z","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":"e6b24c461e59acfa7afdc9bfc5b2953a921524d725338a2995517ffd71767215","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-17T08:59:46Z","title_canon_sha256":"e8acc1c3805dde83c83423834019c2bce6865718e62f3bd5d6eb160b1bc7936f"},"schema_version":"1.0","source":{"id":"2405.10637","kind":"arxiv","version":2}},"canonical_sha256":"cbb2de46dc5161659f343202bbff9f695c120373f248854c3373cf9d66795322","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cbb2de46dc5161659f343202bbff9f695c120373f248854c3373cf9d66795322","first_computed_at":"2026-07-05T08:26:44.814327Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:26:44.814327Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8xfudO31r6Ag5oW33yym5nuMygi8bAlptQR+GAlnYQEc/fXXk+JPF+y+2Ye9CKoe8YJq+qlicCa3htrrvIiqCg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:26:44.814774Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.10637","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:74f544ea25a10b9701f846fc20afc68bf0b8917683bf44f115e183f1f0d1ab70","sha256:5bc2bc4a5383b22493837590e10db30a9e6f511d47f7db614f75a6fba7e2468c"],"state_sha256":"1c611cb2472fdd7f1b17e6c627bd3220ee61567f5ffacbcee24f42b4665a3968"}