{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:REHZO4IT4PZERARN3LJFTP7BMD","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":"5c8d3425b3c7ab0d413cd5aacb8c4a0264d363fd68ca87cbc60a001c14fcd739","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2024-11-18T01:06:12Z","title_canon_sha256":"5ed03f4e01343dc2b3f4773132d6bf3c35f81929f7fd035b43e3f5ace6b06681"},"schema_version":"1.0","source":{"id":"2411.11217","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.11217","created_at":"2026-07-05T09:37:12Z"},{"alias_kind":"arxiv_version","alias_value":"2411.11217v1","created_at":"2026-07-05T09:37:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.11217","created_at":"2026-07-05T09:37:12Z"},{"alias_kind":"pith_short_12","alias_value":"REHZO4IT4PZE","created_at":"2026-07-05T09:37:12Z"},{"alias_kind":"pith_short_16","alias_value":"REHZO4IT4PZERARN","created_at":"2026-07-05T09:37:12Z"},{"alias_kind":"pith_short_8","alias_value":"REHZO4IT","created_at":"2026-07-05T09:37:12Z"}],"graph_snapshots":[{"event_id":"sha256:4c107678101ed3b8a85c664d3bd22dbe80f4c0612fb7d9d7a8466f2ad18ea4af","target":"graph","created_at":"2026-07-05T09:37:12Z","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/2411.11217/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Efficient deployment of large language models, particularly Mixture of Experts (MoE), on resource-constrained platforms presents significant challenges, especially in terms of computational efficiency and memory utilization. The MoE architecture, renowned for its ability to increase model capacity without a proportional increase in inference cost, greatly reduces the token generation latency compared with dense models. However, the large model size makes MoE models inaccessible to individuals without high-end GPUs. In this paper, we propose a high-throughput MoE batch inference system, that si","authors_text":"Ion Stoica, Joseph E. Gonzalez, Matei Zaharia, Peter Schafhalter, Shiyi Cao, Shu Liu, Tyler Griggs, Xiaoxuan Liu, Ying Sheng","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2024-11-18T01:06:12Z","title":"MoE-Lightning: High-Throughput MoE Inference on Memory-constrained GPUs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.11217","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":"sha256:1a2631b201bfe1fba622be94db961903ee2960a235b38bd3b0d7c0e9f02575e6","target":"record","created_at":"2026-07-05T09:37:12Z","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":"5c8d3425b3c7ab0d413cd5aacb8c4a0264d363fd68ca87cbc60a001c14fcd739","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2024-11-18T01:06:12Z","title_canon_sha256":"5ed03f4e01343dc2b3f4773132d6bf3c35f81929f7fd035b43e3f5ace6b06681"},"schema_version":"1.0","source":{"id":"2411.11217","kind":"arxiv","version":1}},"canonical_sha256":"890f977113e3f248822ddad259bfe160f7da57122a966047cdd106f594096d40","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"890f977113e3f248822ddad259bfe160f7da57122a966047cdd106f594096d40","first_computed_at":"2026-07-05T09:37:12.270090Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:37:12.270090Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"n40hKyP5UvJ9q1XyY5fh4mpUuHokDkzq70K+ZiPkqevGIZ0bupPi2KQJnbcnAWZeNCppSruk1AMa/7/f1F9BDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:37:12.270599Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.11217","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1a2631b201bfe1fba622be94db961903ee2960a235b38bd3b0d7c0e9f02575e6","sha256:4c107678101ed3b8a85c664d3bd22dbe80f4c0612fb7d9d7a8466f2ad18ea4af"],"state_sha256":"f427ddcfa988eb7b4ca36c820c3bc2bad0f815a9ad718c295c6e2ebd2f67d08a"}