{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:IUKHAW67LADQ7FFQ6LTVZJOB77","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":"758dcf64b6cc598e7bf257de6e80333d7fd154e87362bd610e63567d1553c21f","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-26T07:33:05Z","title_canon_sha256":"24d72644baf3ed88052f0e1f3de8c592ce9c0f4c11879e16549bd90652972e74"},"schema_version":"1.0","source":{"id":"2402.16363","kind":"arxiv","version":6}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.16363","created_at":"2026-07-05T08:14:22Z"},{"alias_kind":"arxiv_version","alias_value":"2402.16363v6","created_at":"2026-07-05T08:14:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.16363","created_at":"2026-07-05T08:14:22Z"},{"alias_kind":"pith_short_12","alias_value":"IUKHAW67LADQ","created_at":"2026-07-05T08:14:22Z"},{"alias_kind":"pith_short_16","alias_value":"IUKHAW67LADQ7FFQ","created_at":"2026-07-05T08:14:22Z"},{"alias_kind":"pith_short_8","alias_value":"IUKHAW67","created_at":"2026-07-05T08:14:22Z"}],"graph_snapshots":[{"event_id":"sha256:57d48ffb758e51f296a15ad3c594de35c7e76d8c69b60d27d084cfaa7c9d4a28","target":"graph","created_at":"2026-07-05T08:14:22Z","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/2402.16363/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The field of efficient Large Language Model (LLM) inference is rapidly evolving, presenting a unique blend of opportunities and challenges. Although the field has expanded and is vibrant, there hasn't been a concise framework that analyzes the various methods of LLM Inference to provide a clear understanding of this domain. Our survey stands out from traditional literature reviews by not only summarizing the current state of research but also by introducing a framework based on roofline model for systematic analysis of LLM inference techniques. This framework identifies the bottlenecks when de","authors_text":"Beidi Chen, Bingzhe Wu, Chenhao Xue, Guangyu Sun, Kurt Keutzer, Qingyi Gu, Yang Zhou, Yan Yan, Yong Jae Lee, Yuzhang Shang, Zhen Dong, Zhe Zhou, Zhihang Yuan, Zhikai Li","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-26T07:33:05Z","title":"LLM Inference Unveiled: Survey and Roofline Model Insights"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.16363","kind":"arxiv","version":6},"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:e52fd7a293af0db995c37b32302f3a1bed9d4b1696116c219722189a6d59994b","target":"record","created_at":"2026-07-05T08:14:22Z","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":"758dcf64b6cc598e7bf257de6e80333d7fd154e87362bd610e63567d1553c21f","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-26T07:33:05Z","title_canon_sha256":"24d72644baf3ed88052f0e1f3de8c592ce9c0f4c11879e16549bd90652972e74"},"schema_version":"1.0","source":{"id":"2402.16363","kind":"arxiv","version":6}},"canonical_sha256":"4514705bdf58070f94b0f2e75ca5c1fff2a9d0d3e6d926080884245cb5225207","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4514705bdf58070f94b0f2e75ca5c1fff2a9d0d3e6d926080884245cb5225207","first_computed_at":"2026-07-05T08:14:22.252642Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:14:22.252642Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5gAoxoeiITjRLS24T1+F5n1x3cL8we8HTOLqqCuPEpYy1wf0p9PJzdbSxehhHv4CeQs8u61zddC9IBDRka6dBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:14:22.253131Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.16363","source_kind":"arxiv","source_version":6}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e52fd7a293af0db995c37b32302f3a1bed9d4b1696116c219722189a6d59994b","sha256:57d48ffb758e51f296a15ad3c594de35c7e76d8c69b60d27d084cfaa7c9d4a28"],"state_sha256":"ec193a0e98242ef739e35f1756f43a3e4b096d0d6619d9470ac3eb21c7671f80"}