{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:VXKTKKIGE7HH6ZVA2V6MEJGHYR","short_pith_number":"pith:VXKTKKIG","schema_version":"1.0","canonical_sha256":"add535290627ce7f66a0d57cc224c7c47ed24fec7b3ecfaf005ad19cc3a18123","source":{"kind":"arxiv","id":"2211.10017","version":1},"attestation_state":"computed","paper":{"title":"Who Says Elephants Can't Run: Bringing Large Scale MoE Models into Cloud Scale Production","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Hany Hassan Awadalla, Raffy Fahim, Rawn Henry, Young Jin Kim","submitted_at":"2022-11-18T03:43:52Z","abstract_excerpt":"Mixture of Experts (MoE) models with conditional execution of sparsely activated layers have enabled training models with a much larger number of parameters. As a result, these models have achieved significantly better quality on various natural language processing tasks including machine translation. However, it remains challenging to deploy such models in real-life scenarios due to the large memory requirements and inefficient inference. In this work, we introduce a highly efficient inference framework with several optimization approaches to accelerate the computation of sparse models and cu"},"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":"2211.10017","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-11-18T03:43:52Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"e6562b97f129f27c500ac09e3676e052e14c7997d7c8368f4ae34855588693e0","abstract_canon_sha256":"126898fed73642613ea52a0604d817c48fa8357a3b9bb83aa3b343372e26c6f8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:17:17.236476Z","signature_b64":"PsuxkePDVzYDn6r/sYNOYVAMrTW8ojniJPSO0vKeWo87ypmsBGujgRSBy2u0cN7ZOM6ZAB9uAqUkHf4s4xoQDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"add535290627ce7f66a0d57cc224c7c47ed24fec7b3ecfaf005ad19cc3a18123","last_reissued_at":"2026-07-05T05:17:17.235927Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:17:17.235927Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Who Says Elephants Can't Run: Bringing Large Scale MoE Models into Cloud Scale Production","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Hany Hassan Awadalla, Raffy Fahim, Rawn Henry, Young Jin Kim","submitted_at":"2022-11-18T03:43:52Z","abstract_excerpt":"Mixture of Experts (MoE) models with conditional execution of sparsely activated layers have enabled training models with a much larger number of parameters. As a result, these models have achieved significantly better quality on various natural language processing tasks including machine translation. However, it remains challenging to deploy such models in real-life scenarios due to the large memory requirements and inefficient inference. In this work, we introduce a highly efficient inference framework with several optimization approaches to accelerate the computation of sparse models and cu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.10017","kind":"arxiv","version":1},"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/2211.10017/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":"2211.10017","created_at":"2026-07-05T05:17:17.235993+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.10017v1","created_at":"2026-07-05T05:17:17.235993+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.10017","created_at":"2026-07-05T05:17:17.235993+00:00"},{"alias_kind":"pith_short_12","alias_value":"VXKTKKIGE7HH","created_at":"2026-07-05T05:17:17.235993+00:00"},{"alias_kind":"pith_short_16","alias_value":"VXKTKKIGE7HH6ZVA","created_at":"2026-07-05T05:17:17.235993+00:00"},{"alias_kind":"pith_short_8","alias_value":"VXKTKKIG","created_at":"2026-07-05T05:17:17.235993+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2306.00978","citing_title":"AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02715","citing_title":"FluxMoE: Decoupling Expert Residency for High-Performance MoE Serving","ref_index":30,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VXKTKKIGE7HH6ZVA2V6MEJGHYR","json":"https://pith.science/pith/VXKTKKIGE7HH6ZVA2V6MEJGHYR.json","graph_json":"https://pith.science/api/pith-number/VXKTKKIGE7HH6ZVA2V6MEJGHYR/graph.json","events_json":"https://pith.science/api/pith-number/VXKTKKIGE7HH6ZVA2V6MEJGHYR/events.json","paper":"https://pith.science/paper/VXKTKKIG"},"agent_actions":{"view_html":"https://pith.science/pith/VXKTKKIGE7HH6ZVA2V6MEJGHYR","download_json":"https://pith.science/pith/VXKTKKIGE7HH6ZVA2V6MEJGHYR.json","view_paper":"https://pith.science/paper/VXKTKKIG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.10017&json=true","fetch_graph":"https://pith.science/api/pith-number/VXKTKKIGE7HH6ZVA2V6MEJGHYR/graph.json","fetch_events":"https://pith.science/api/pith-number/VXKTKKIGE7HH6ZVA2V6MEJGHYR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VXKTKKIGE7HH6ZVA2V6MEJGHYR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VXKTKKIGE7HH6ZVA2V6MEJGHYR/action/storage_attestation","attest_author":"https://pith.science/pith/VXKTKKIGE7HH6ZVA2V6MEJGHYR/action/author_attestation","sign_citation":"https://pith.science/pith/VXKTKKIGE7HH6ZVA2V6MEJGHYR/action/citation_signature","submit_replication":"https://pith.science/pith/VXKTKKIGE7HH6ZVA2V6MEJGHYR/action/replication_record"}},"created_at":"2026-07-05T05:17:17.235993+00:00","updated_at":"2026-07-05T05:17:17.235993+00:00"}