{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:WK54FMIPOFFBSE65ETSIO4MX5N","short_pith_number":"pith:WK54FMIP","schema_version":"1.0","canonical_sha256":"b2bbc2b10f714a1913dd24e4877197eb791936a42c716db54309f9f021e151ef","source":{"kind":"arxiv","id":"2312.15234","version":2},"attestation_state":"computed","paper":{"title":"Towards Efficient Generative Large Language Model Serving: A Survey from Algorithms to Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.DC","cs.PF"],"primary_cat":"cs.LG","authors_text":"Gabriele Oliaro, Hongyi Jin, Tianqi Chen, Xinhao Cheng, Xupeng Miao, Zhihao Jia, Zhihao Zhang","submitted_at":"2023-12-23T11:57:53Z","abstract_excerpt":"In the rapidly evolving landscape of artificial intelligence (AI), generative large language models (LLMs) stand at the forefront, revolutionizing how we interact with our data. However, the computational intensity and memory consumption of deploying these models present substantial challenges in terms of serving efficiency, particularly in scenarios demanding low latency and high throughput. This survey addresses the imperative need for efficient LLM serving methodologies from a machine learning system (MLSys) research perspective, standing at the crux of advanced AI innovations and practical"},"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":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2312.15234","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-12-23T11:57:53Z","cross_cats_sorted":["cs.AI","cs.DC","cs.PF"],"title_canon_sha256":"46aea9840077d9c7a2e617d9ce48096e4b98190e2e740346f52ca1f589c64506","abstract_canon_sha256":"0d65ec35d688393ddc6a8bad9155995ddfc848c872b9f26afef75818b4459200"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:41:33.212686Z","signature_b64":"ilAfn6gqa9CEKDkeE5YGDcXX8HmTthfBXrGKBNqUE0g7jIkP8eLbD0krTYkOy7sjRDB3OItI4uREHf1foXHXBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b2bbc2b10f714a1913dd24e4877197eb791936a42c716db54309f9f021e151ef","last_reissued_at":"2026-07-05T11:41:33.212182Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:41:33.212182Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Efficient Generative Large Language Model Serving: A Survey from Algorithms to Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.DC","cs.PF"],"primary_cat":"cs.LG","authors_text":"Gabriele Oliaro, Hongyi Jin, Tianqi Chen, Xinhao Cheng, Xupeng Miao, Zhihao Jia, Zhihao Zhang","submitted_at":"2023-12-23T11:57:53Z","abstract_excerpt":"In the rapidly evolving landscape of artificial intelligence (AI), generative large language models (LLMs) stand at the forefront, revolutionizing how we interact with our data. However, the computational intensity and memory consumption of deploying these models present substantial challenges in terms of serving efficiency, particularly in scenarios demanding low latency and high throughput. This survey addresses the imperative need for efficient LLM serving methodologies from a machine learning system (MLSys) research perspective, standing at the crux of advanced AI innovations and practical"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.15234","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2312.15234/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"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":"2312.15234","created_at":"2026-07-05T11:41:33.212232+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.15234v2","created_at":"2026-07-05T11:41:33.212232+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.15234","created_at":"2026-07-05T11:41:33.212232+00:00"},{"alias_kind":"pith_short_12","alias_value":"WK54FMIPOFFB","created_at":"2026-07-05T11:41:33.212232+00:00"},{"alias_kind":"pith_short_16","alias_value":"WK54FMIPOFFBSE65","created_at":"2026-07-05T11:41:33.212232+00:00"},{"alias_kind":"pith_short_8","alias_value":"WK54FMIP","created_at":"2026-07-05T11:41:33.212232+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.08057","citing_title":"Towards Efficient Large Language Model Serving: A Survey on System-Aware KV Cache Optimization","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"2606.21712","citing_title":"BatchGen: An Architecture for Scalable and Efficient Batch Inference","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2606.06453","citing_title":"Vortex: Efficient and Programmable Sparse Attention Serving for AI Agents","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2602.04163","citing_title":"BPDQ: Bit-Plane Decomposition Quantization on a Variable Grid for Large Language Models","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2512.09427","citing_title":"ODMA: On-Demand Memory Allocation Strategy for LLM Serving on LPDDR-Class Accelerators","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2404.13501","citing_title":"A Survey on the Memory Mechanism of Large Language Model based Agents","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2404.14294","citing_title":"A Survey on Efficient Inference for Large Language Models","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WK54FMIPOFFBSE65ETSIO4MX5N","json":"https://pith.science/pith/WK54FMIPOFFBSE65ETSIO4MX5N.json","graph_json":"https://pith.science/api/pith-number/WK54FMIPOFFBSE65ETSIO4MX5N/graph.json","events_json":"https://pith.science/api/pith-number/WK54FMIPOFFBSE65ETSIO4MX5N/events.json","paper":"https://pith.science/paper/WK54FMIP"},"agent_actions":{"view_html":"https://pith.science/pith/WK54FMIPOFFBSE65ETSIO4MX5N","download_json":"https://pith.science/pith/WK54FMIPOFFBSE65ETSIO4MX5N.json","view_paper":"https://pith.science/paper/WK54FMIP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.15234&json=true","fetch_graph":"https://pith.science/api/pith-number/WK54FMIPOFFBSE65ETSIO4MX5N/graph.json","fetch_events":"https://pith.science/api/pith-number/WK54FMIPOFFBSE65ETSIO4MX5N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WK54FMIPOFFBSE65ETSIO4MX5N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WK54FMIPOFFBSE65ETSIO4MX5N/action/storage_attestation","attest_author":"https://pith.science/pith/WK54FMIPOFFBSE65ETSIO4MX5N/action/author_attestation","sign_citation":"https://pith.science/pith/WK54FMIPOFFBSE65ETSIO4MX5N/action/citation_signature","submit_replication":"https://pith.science/pith/WK54FMIPOFFBSE65ETSIO4MX5N/action/replication_record"}},"created_at":"2026-07-05T11:41:33.212232+00:00","updated_at":"2026-07-05T11:41:33.212232+00:00"}