{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ND2G5534I2P7P2MBJXOK2OO5UI","short_pith_number":"pith:ND2G5534","schema_version":"1.0","canonical_sha256":"68f46ef77c469ff7e9814ddcad39dda2047d113fd1542d4f5437c4550aa951f3","source":{"kind":"arxiv","id":"2407.14417","version":2},"attestation_state":"computed","paper":{"title":"Mixture of Experts with Mixture of Precisions for Tuning Quality of Service","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.PF"],"primary_cat":"cs.DC","authors_text":"Abdolah Amirany, HamidReza Imani, Tarek El-Ghazawi","submitted_at":"2024-07-19T15:42:49Z","abstract_excerpt":"The increasing demand for deploying large Mixture-of-Experts (MoE) models in resource-constrained environments necessitates efficient approaches to address their high memory and computational requirements challenges. Moreover, given that tasks come in different user-defined constraints and the available resources change over time in multi-tenant environments, it is necessary to design an approach which provides a flexible configuration space. This paper presents an adaptive serving approach for the efficient deployment of MoE models, capitalizing on partial quantization of the experts. By dyna"},"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":"2407.14417","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2024-07-19T15:42:49Z","cross_cats_sorted":["cs.AI","cs.LG","cs.PF"],"title_canon_sha256":"a49af5b7c83870425ecb95841953bd77046d416f34da1c193098ad357a2a0cfd","abstract_canon_sha256":"8ea86670dc9919adc010eb8559ee49822a6549cefad524c9231f41454bdf4d50"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:04:38.220462Z","signature_b64":"Odt6woL7KQl/z4leVJm2xt5CqRGSnCo0Ms9WFa6qZF3WktYGPelXulE1cS3tbdVb5HQy0POiZ15ZDMoyx7RfBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"68f46ef77c469ff7e9814ddcad39dda2047d113fd1542d4f5437c4550aa951f3","last_reissued_at":"2026-07-05T09:04:38.220042Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:04:38.220042Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mixture of Experts with Mixture of Precisions for Tuning Quality of Service","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.PF"],"primary_cat":"cs.DC","authors_text":"Abdolah Amirany, HamidReza Imani, Tarek El-Ghazawi","submitted_at":"2024-07-19T15:42:49Z","abstract_excerpt":"The increasing demand for deploying large Mixture-of-Experts (MoE) models in resource-constrained environments necessitates efficient approaches to address their high memory and computational requirements challenges. Moreover, given that tasks come in different user-defined constraints and the available resources change over time in multi-tenant environments, it is necessary to design an approach which provides a flexible configuration space. This paper presents an adaptive serving approach for the efficient deployment of MoE models, capitalizing on partial quantization of the experts. By dyna"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.14417","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/2407.14417/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":"2407.14417","created_at":"2026-07-05T09:04:38.220097+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.14417v2","created_at":"2026-07-05T09:04:38.220097+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.14417","created_at":"2026-07-05T09:04:38.220097+00:00"},{"alias_kind":"pith_short_12","alias_value":"ND2G5534I2P7","created_at":"2026-07-05T09:04:38.220097+00:00"},{"alias_kind":"pith_short_16","alias_value":"ND2G5534I2P7P2MB","created_at":"2026-07-05T09:04:38.220097+00:00"},{"alias_kind":"pith_short_8","alias_value":"ND2G5534","created_at":"2026-07-05T09:04:38.220097+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.16352","citing_title":"Mixture of Experts (MoE): A Big Data Perspective","ref_index":74,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ND2G5534I2P7P2MBJXOK2OO5UI","json":"https://pith.science/pith/ND2G5534I2P7P2MBJXOK2OO5UI.json","graph_json":"https://pith.science/api/pith-number/ND2G5534I2P7P2MBJXOK2OO5UI/graph.json","events_json":"https://pith.science/api/pith-number/ND2G5534I2P7P2MBJXOK2OO5UI/events.json","paper":"https://pith.science/paper/ND2G5534"},"agent_actions":{"view_html":"https://pith.science/pith/ND2G5534I2P7P2MBJXOK2OO5UI","download_json":"https://pith.science/pith/ND2G5534I2P7P2MBJXOK2OO5UI.json","view_paper":"https://pith.science/paper/ND2G5534","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.14417&json=true","fetch_graph":"https://pith.science/api/pith-number/ND2G5534I2P7P2MBJXOK2OO5UI/graph.json","fetch_events":"https://pith.science/api/pith-number/ND2G5534I2P7P2MBJXOK2OO5UI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ND2G5534I2P7P2MBJXOK2OO5UI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ND2G5534I2P7P2MBJXOK2OO5UI/action/storage_attestation","attest_author":"https://pith.science/pith/ND2G5534I2P7P2MBJXOK2OO5UI/action/author_attestation","sign_citation":"https://pith.science/pith/ND2G5534I2P7P2MBJXOK2OO5UI/action/citation_signature","submit_replication":"https://pith.science/pith/ND2G5534I2P7P2MBJXOK2OO5UI/action/replication_record"}},"created_at":"2026-07-05T09:04:38.220097+00:00","updated_at":"2026-07-05T09:04:38.220097+00:00"}