{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:F22MPUSCVMTNP2ZWQIPGUBRPBC","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":"b23c49586ee5e71c0df0ac911bedd1b3b653b4055b61101a22d55f4fb9b13984","cross_cats_sorted":["cs.AI","cs.LG","cs.PF"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AR","submitted_at":"2025-04-19T13:17:34Z","title_canon_sha256":"bda410aaa4f6721f12ca9933c6ac632499c61955f9f72d5ad675c86904246b4c"},"schema_version":"1.0","source":{"id":"2505.03756","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.03756","created_at":"2026-07-05T10:59:30Z"},{"alias_kind":"arxiv_version","alias_value":"2505.03756v1","created_at":"2026-07-05T10:59:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.03756","created_at":"2026-07-05T10:59:30Z"},{"alias_kind":"pith_short_12","alias_value":"F22MPUSCVMTN","created_at":"2026-07-05T10:59:30Z"},{"alias_kind":"pith_short_16","alias_value":"F22MPUSCVMTNP2ZW","created_at":"2026-07-05T10:59:30Z"},{"alias_kind":"pith_short_8","alias_value":"F22MPUSC","created_at":"2026-07-05T10:59:30Z"}],"graph_snapshots":[{"event_id":"sha256:738582ec0c4016d2ea7977437b440d74c9fe40b2f6c20030317f6d61c37098b3","target":"graph","created_at":"2026-07-05T10:59:30Z","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/2505.03756/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multiple Low-Rank Adapters (Multi-LoRAs) are gaining popularity for task-specific Large Language Model (LLM) applications. For multi-LoRA serving, caching hot KV caches and LoRA adapters in high bandwidth memory of accelerations can improve inference performance. However, existing Multi-LoRA inference systems fail to optimize serving performance like Time-To-First-Toke (TTFT), neglecting usage dependencies when caching LoRAs and KVs. We therefore propose FASTLIBRA, a Multi-LoRA caching system to optimize the serving performance. FASTLIBRA comprises a dependency-aware cache manager and a perfor","authors_text":"Hang Zhang, Jiuchen Shi, Minyi Guo, Quan Chen, Yixiao Wang, Yizhou Shan","cross_cats":["cs.AI","cs.LG","cs.PF"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AR","submitted_at":"2025-04-19T13:17:34Z","title":"Improving the Serving Performance of Multi-LoRA Large Language Models via Efficient LoRA and KV Cache Management"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.03756","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":"sha256:098c25b310406968d9d88ee9c4f97d0478436e829ff249fc6d36d2f1f229db61","target":"record","created_at":"2026-07-05T10:59:30Z","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":"b23c49586ee5e71c0df0ac911bedd1b3b653b4055b61101a22d55f4fb9b13984","cross_cats_sorted":["cs.AI","cs.LG","cs.PF"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AR","submitted_at":"2025-04-19T13:17:34Z","title_canon_sha256":"bda410aaa4f6721f12ca9933c6ac632499c61955f9f72d5ad675c86904246b4c"},"schema_version":"1.0","source":{"id":"2505.03756","kind":"arxiv","version":1}},"canonical_sha256":"2eb4c7d242ab26d7eb36821e6a062f089a330e595e552e25bc184ccc03b216d8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2eb4c7d242ab26d7eb36821e6a062f089a330e595e552e25bc184ccc03b216d8","first_computed_at":"2026-07-05T10:59:30.460009Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:59:30.460009Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uOTlEPVksTGjuiBnJPi5DqHsrrSTlNE2YTPTf4NDNqy1WeiQeD1S3WyohzPDSxJscAb1CCeO/SN1Q/ln7KJvDw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:59:30.460504Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.03756","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:098c25b310406968d9d88ee9c4f97d0478436e829ff249fc6d36d2f1f229db61","sha256:738582ec0c4016d2ea7977437b440d74c9fe40b2f6c20030317f6d61c37098b3"],"state_sha256":"d4b503d43f89c0c969d82010bbccf7c76a6a981ebb631058e16942b5cd1d5d96"}