{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:HPCYHLSY4N5IZ3T74VYH44OOCW","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":"e6f0d28e9e3092841b19d9efdd7b6c40676f22ac3540bebd3e29342676059218","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2025-04-03T04:20:44Z","title_canon_sha256":"746867b3dbc00cedbffc7c44947609f22b964b6d9803d065f909b49fc21cefea"},"schema_version":"1.0","source":{"id":"2504.02263","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.02263","created_at":"2026-07-05T11:43:31Z"},{"alias_kind":"arxiv_version","alias_value":"2504.02263v4","created_at":"2026-07-05T11:43:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.02263","created_at":"2026-07-05T11:43:31Z"},{"alias_kind":"pith_short_12","alias_value":"HPCYHLSY4N5I","created_at":"2026-07-05T11:43:31Z"},{"alias_kind":"pith_short_16","alias_value":"HPCYHLSY4N5IZ3T7","created_at":"2026-07-05T11:43:31Z"},{"alias_kind":"pith_short_8","alias_value":"HPCYHLSY","created_at":"2026-07-05T11:43:31Z"}],"graph_snapshots":[{"event_id":"sha256:15afbc1c16a7ddba5c5b8b1a214dee0630b3a5f89f1f60bf053cfb3bf2b4cc79","target":"graph","created_at":"2026-07-05T11:43:31Z","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/2504.02263/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Mixture-of-Experts (MoE) showcases tremendous potential to scale large language models (LLMs) with enhanced performance and reduced computational complexity. However, its sparsely activated architecture shifts feed-forward networks (FFNs) from being compute-intensive to memory-intensive during inference, leading to substantially lower GPU utilization and increased operational costs.\n  We present MegaScale-Infer, an efficient and cost-effective system for serving large-scale MoE models. MegaScale-Infer disaggregates attention and FFN modules within each model layer, enabling independent scaling","authors_text":"Cesar A. Stuardo, Chao Jin, Dongyang Wang, Haibin Lin, Haoran Wei, Huaping Zhou, Jianxi Ye, Jianzhe Xiao, Lingjun Liu, Li-wen Chang, Peng Wu, Ruidong Zhu, Xiao Yu, Xin Jin, Xinlei Zhang, Xin Liu, Xinyi Zhang, Xuanzhe Liu, Yang Cheng, Ziheng Jiang","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2025-04-03T04:20:44Z","title":"MegaScale-Infer: Serving Mixture-of-Experts at Scale with Disaggregated Expert Parallelism"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.02263","kind":"arxiv","version":4},"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":"sha256:6806cc5830010a87d60557571de872b0740f948e3bf48cfa7d28a423f7e9af40","target":"record","created_at":"2026-07-05T11:43:31Z","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":"e6f0d28e9e3092841b19d9efdd7b6c40676f22ac3540bebd3e29342676059218","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2025-04-03T04:20:44Z","title_canon_sha256":"746867b3dbc00cedbffc7c44947609f22b964b6d9803d065f909b49fc21cefea"},"schema_version":"1.0","source":{"id":"2504.02263","kind":"arxiv","version":4}},"canonical_sha256":"3bc583ae58e37a8cee7fe5707e71ce1582f12dc5226a37219d4a6141e397c157","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3bc583ae58e37a8cee7fe5707e71ce1582f12dc5226a37219d4a6141e397c157","first_computed_at":"2026-07-05T11:43:31.471388Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:43:31.471388Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7xT+wC/U0Q+eR8bI9/iJpUfO9hnJETZatRDjbtwIqAcyfA1wTyT1FLNNHh4T/QWrbhWV8/XD5dsRkp1h96aNAg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:43:31.471918Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.02263","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6806cc5830010a87d60557571de872b0740f948e3bf48cfa7d28a423f7e9af40","sha256:15afbc1c16a7ddba5c5b8b1a214dee0630b3a5f89f1f60bf053cfb3bf2b4cc79"],"state_sha256":"722ca704dd37a566dd1fd39f4ec32c1a98f6dfe3f2ed2555d45ad5aae8f6a882"}