{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:VFM4H2X4QLKUSESVGU6GVVGKAZ","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":"bd55e1727e13f338c3188b7b4d0e6a63f99f32ba622dc38997c336164ce5e312","cross_cats_sorted":["cs.DC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-03T04:25:46Z","title_canon_sha256":"6c349032c15c54eb777fee786eff34239ad046dffbaa612523cc846b2021df8f"},"schema_version":"1.0","source":{"id":"2411.01433","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.01433","created_at":"2026-07-05T09:31:50Z"},{"alias_kind":"arxiv_version","alias_value":"2411.01433v2","created_at":"2026-07-05T09:31:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.01433","created_at":"2026-07-05T09:31:50Z"},{"alias_kind":"pith_short_12","alias_value":"VFM4H2X4QLKU","created_at":"2026-07-05T09:31:50Z"},{"alias_kind":"pith_short_16","alias_value":"VFM4H2X4QLKUSESV","created_at":"2026-07-05T09:31:50Z"},{"alias_kind":"pith_short_8","alias_value":"VFM4H2X4","created_at":"2026-07-05T09:31:50Z"}],"graph_snapshots":[{"event_id":"sha256:eada747eae2ef6b7114b5c15eca15dc20395f10acd7ea20e30b4b36291def0de","target":"graph","created_at":"2026-07-05T09:31:50Z","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/2411.01433/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The Mixture-of-Experts (MoE) architecture has demonstrated significant advantages in the era of Large Language Models (LLMs), offering enhanced capabilities with reduced inference costs. However, deploying MoE-based LLMs on memoryconstrained edge devices remains challenging due to their substantial memory requirements. While existing expertoffloading methods alleviate the memory requirements, they often incur significant expert-loading costs or compromise model accuracy. We present HOBBIT, a mixed precision expert offloading system to enable flexible and efficient MoE inference. Our key insigh","authors_text":"Chao Li, Jiacheng Liu, Jing Wang, Minyi Guo, Peng Tang, Pheng-Ann Heng, Xiaofeng Hou, Yifei Pu","cross_cats":["cs.DC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-03T04:25:46Z","title":"HOBBIT: A Mixed Precision Expert Offloading System for Fast MoE Inference"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.01433","kind":"arxiv","version":2},"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":"sha256:33d2a92d10e2fec7c0a32be16397f60a1e25bd0764829187212b1ac58ec937c4","target":"record","created_at":"2026-07-05T09:31:50Z","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":"bd55e1727e13f338c3188b7b4d0e6a63f99f32ba622dc38997c336164ce5e312","cross_cats_sorted":["cs.DC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-03T04:25:46Z","title_canon_sha256":"6c349032c15c54eb777fee786eff34239ad046dffbaa612523cc846b2021df8f"},"schema_version":"1.0","source":{"id":"2411.01433","kind":"arxiv","version":2}},"canonical_sha256":"a959c3eafc82d5491255353c6ad4ca06570ca230a97c5fd18e1001760a710be7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a959c3eafc82d5491255353c6ad4ca06570ca230a97c5fd18e1001760a710be7","first_computed_at":"2026-07-05T09:31:50.959999Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:31:50.959999Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FYPeoKwnuhfb6Qjnv3NnqRj+covO2T+1JtbQrGNiUZlV7Gfhv/ts4kxekOest+97dpHz2jz/aMdGS/F8HUskDg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:31:50.960551Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.01433","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:33d2a92d10e2fec7c0a32be16397f60a1e25bd0764829187212b1ac58ec937c4","sha256:eada747eae2ef6b7114b5c15eca15dc20395f10acd7ea20e30b4b36291def0de"],"state_sha256":"e52fe34b7fa212f7fcc4352352c79ffcd9fd625b936e004cf91d54766c817daf"}