{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ABCKJ6RFD3DKDZLIXANDCJT4QF","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":"5f4fbc588be27a44d6aba290bc243f5b1f6e859163457115837dc0beef8ae011","cross_cats_sorted":["cs.DC","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-12-24T02:27:44Z","title_canon_sha256":"bdad2799d3e790e98bf5c68845f29879c2aa0d4d7dc62643130c09fb700b7955"},"schema_version":"1.0","source":{"id":"2412.18106","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.18106","created_at":"2026-07-05T09:54:07Z"},{"alias_kind":"arxiv_version","alias_value":"2412.18106v1","created_at":"2026-07-05T09:54:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.18106","created_at":"2026-07-05T09:54:07Z"},{"alias_kind":"pith_short_12","alias_value":"ABCKJ6RFD3DK","created_at":"2026-07-05T09:54:07Z"},{"alias_kind":"pith_short_16","alias_value":"ABCKJ6RFD3DKDZLI","created_at":"2026-07-05T09:54:07Z"},{"alias_kind":"pith_short_8","alias_value":"ABCKJ6RF","created_at":"2026-07-05T09:54:07Z"}],"graph_snapshots":[{"event_id":"sha256:a186b246632f9260324e5e173a85c4e22c267b7a20fa922d6c4f22d278ce6f40","target":"graph","created_at":"2026-07-05T09:54:07Z","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/2412.18106/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Meeting growing demands for low latency and cost efficiency in production-grade large language model (LLM) serving systems requires integrating advanced optimization techniques. However, dynamic and unpredictable input-output lengths of LLM, compounded by these optimizations, exacerbate the issues of workload variability, making it difficult to maintain high efficiency on AI accelerators, especially DSAs with tile-based programming models. To address this challenge, we introduce XY-Serve, a versatile, Ascend native, end-to-end production LLM-serving system. The core idea is an abstraction mech","authors_text":"Dingcheng Jiang, Fengfan Hou, Guoping Long, Hongjie Si, Jing Li, Mingcong Song, Runqiu Xiao, Shouyi Yin, Wei Wei, Xinru Tang, Yang Hu, Yipeng Ma","cross_cats":["cs.DC","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-12-24T02:27:44Z","title":"Tackling the Dynamicity in a Production LLM Serving System with SOTA Optimizations via Hybrid Prefill/Decode/Verify Scheduling on Efficient Meta-kernels"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.18106","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":"sha256:94fb31049fc79c10463a5cefbc4e71e8316543aeb024fc2a13eb4698eee7eff0","target":"record","created_at":"2026-07-05T09:54:07Z","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":"5f4fbc588be27a44d6aba290bc243f5b1f6e859163457115837dc0beef8ae011","cross_cats_sorted":["cs.DC","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-12-24T02:27:44Z","title_canon_sha256":"bdad2799d3e790e98bf5c68845f29879c2aa0d4d7dc62643130c09fb700b7955"},"schema_version":"1.0","source":{"id":"2412.18106","kind":"arxiv","version":1}},"canonical_sha256":"0044a4fa251ec6a1e568b81a31267c816e6a33a284a1bf5aaee5bbed14ba8bb7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0044a4fa251ec6a1e568b81a31267c816e6a33a284a1bf5aaee5bbed14ba8bb7","first_computed_at":"2026-07-05T09:54:07.696828Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:54:07.696828Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fnmyjPXS5lX8bSMRcX6M6VLN+SEAMDRrKxBX268ZMVt1IvYYRs0wMda/4NUeEzog2SUKGhb4blyO1747sUfVBw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:54:07.697295Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.18106","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:94fb31049fc79c10463a5cefbc4e71e8316543aeb024fc2a13eb4698eee7eff0","sha256:a186b246632f9260324e5e173a85c4e22c267b7a20fa922d6c4f22d278ce6f40"],"state_sha256":"eb5c41498eaba837f2b04a72e4624ba2d1b2bfc2fb8d9852f85e1d024310a44a"}