{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:4TQBR6TB2LWMZ6BLA7JQFKBLW6","short_pith_number":"pith:4TQBR6TB","canonical_record":{"source":{"id":"2402.07033","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-10T19:54:08Z","cross_cats_sorted":["cs.AI","cs.DC","cs.OS"],"title_canon_sha256":"6e0bfbfa6b733e822383d513bab3bf37f19cf54a980a21a67d1975d99a3fe56e","abstract_canon_sha256":"927c4391f7c4feddc73527dd7c9b06690c3c01825dc9b4bb1320c4ff42882f93"},"schema_version":"1.0"},"canonical_sha256":"e4e018fa61d2ecccf82b07d302a82bb78a9874b236308717384d239ca1e962ac","source":{"kind":"arxiv","id":"2402.07033","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.07033","created_at":"2026-07-05T10:56:32Z"},{"alias_kind":"arxiv_version","alias_value":"2402.07033v3","created_at":"2026-07-05T10:56:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.07033","created_at":"2026-07-05T10:56:32Z"},{"alias_kind":"pith_short_12","alias_value":"4TQBR6TB2LWM","created_at":"2026-07-05T10:56:32Z"},{"alias_kind":"pith_short_16","alias_value":"4TQBR6TB2LWMZ6BL","created_at":"2026-07-05T10:56:32Z"},{"alias_kind":"pith_short_8","alias_value":"4TQBR6TB","created_at":"2026-07-05T10:56:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:4TQBR6TB2LWMZ6BLA7JQFKBLW6","target":"record","payload":{"canonical_record":{"source":{"id":"2402.07033","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-10T19:54:08Z","cross_cats_sorted":["cs.AI","cs.DC","cs.OS"],"title_canon_sha256":"6e0bfbfa6b733e822383d513bab3bf37f19cf54a980a21a67d1975d99a3fe56e","abstract_canon_sha256":"927c4391f7c4feddc73527dd7c9b06690c3c01825dc9b4bb1320c4ff42882f93"},"schema_version":"1.0"},"canonical_sha256":"e4e018fa61d2ecccf82b07d302a82bb78a9874b236308717384d239ca1e962ac","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:56:32.151165Z","signature_b64":"oSFUapgBMfl9iA56+59OMVH3jn61nmiu779vVy4r9gX71oo1D+yfd1cfnb3gFZplGrnEkcOtcMzGPlfnb8yBAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e4e018fa61d2ecccf82b07d302a82bb78a9874b236308717384d239ca1e962ac","last_reissued_at":"2026-07-05T10:56:32.150676Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:56:32.150676Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.07033","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:56:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QvmeogmxyTsJTopk5PIN7KcVg/QfiOBFFxkpbWHaXmnG5EhwA6YCLM4O/uTu/m+4aTqX9UjN2EHsVE/bUx6lAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T21:00:59.471076Z"},"content_sha256":"f585e96439dc969d38f9e43ac346c7a284bf8b044243305f69aa720de3a47867","schema_version":"1.0","event_id":"sha256:f585e96439dc969d38f9e43ac346c7a284bf8b044243305f69aa720de3a47867"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:4TQBR6TB2LWMZ6BLA7JQFKBLW6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Fiddler: CPU-GPU Orchestration for Fast Inference of Mixture-of-Experts Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.DC","cs.OS"],"primary_cat":"cs.LG","authors_text":"Baris Kasikci, Kan Zhu, Keisuke Kamahori, Tian Tang, Yile Gu","submitted_at":"2024-02-10T19:54:08Z","abstract_excerpt":"Large Language Models (LLMs) with the Mixture-of-Experts (MoE) architectures have shown promising performance on various tasks. However, due to the huge model sizes, running them in resource-constrained environments where the GPU memory is not abundant is challenging. Some existing systems propose to use CPU resources to solve that, but they either suffer from the significant overhead of frequently moving data between CPU and GPU, or fail to consider distinct characteristics of CPUs and GPUs. This paper proposes Fiddler, a resource-efficient inference system for MoE models with limited GPU res"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.07033","kind":"arxiv","version":3},"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/2402.07033/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:56:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"I5vgr0vdBH5HCy/VLjyWx78276VCWO5etP7RnOrxH/oEv0dqDtyVnDx+MqjSgoZ2WWVNTwdjER/VrnqLVte4BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T21:00:59.471582Z"},"content_sha256":"7c85be5feb07f68fe73ac6dc381e9e60e68605576e1cc6ba6968d9a7617fba41","schema_version":"1.0","event_id":"sha256:7c85be5feb07f68fe73ac6dc381e9e60e68605576e1cc6ba6968d9a7617fba41"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4TQBR6TB2LWMZ6BLA7JQFKBLW6/bundle.json","state_url":"https://pith.science/pith/4TQBR6TB2LWMZ6BLA7JQFKBLW6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4TQBR6TB2LWMZ6BLA7JQFKBLW6/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-14T21:00:59Z","links":{"resolver":"https://pith.science/pith/4TQBR6TB2LWMZ6BLA7JQFKBLW6","bundle":"https://pith.science/pith/4TQBR6TB2LWMZ6BLA7JQFKBLW6/bundle.json","state":"https://pith.science/pith/4TQBR6TB2LWMZ6BLA7JQFKBLW6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4TQBR6TB2LWMZ6BLA7JQFKBLW6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:4TQBR6TB2LWMZ6BLA7JQFKBLW6","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":"927c4391f7c4feddc73527dd7c9b06690c3c01825dc9b4bb1320c4ff42882f93","cross_cats_sorted":["cs.AI","cs.DC","cs.OS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-10T19:54:08Z","title_canon_sha256":"6e0bfbfa6b733e822383d513bab3bf37f19cf54a980a21a67d1975d99a3fe56e"},"schema_version":"1.0","source":{"id":"2402.07033","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.07033","created_at":"2026-07-05T10:56:32Z"},{"alias_kind":"arxiv_version","alias_value":"2402.07033v3","created_at":"2026-07-05T10:56:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.07033","created_at":"2026-07-05T10:56:32Z"},{"alias_kind":"pith_short_12","alias_value":"4TQBR6TB2LWM","created_at":"2026-07-05T10:56:32Z"},{"alias_kind":"pith_short_16","alias_value":"4TQBR6TB2LWMZ6BL","created_at":"2026-07-05T10:56:32Z"},{"alias_kind":"pith_short_8","alias_value":"4TQBR6TB","created_at":"2026-07-05T10:56:32Z"}],"graph_snapshots":[{"event_id":"sha256:7c85be5feb07f68fe73ac6dc381e9e60e68605576e1cc6ba6968d9a7617fba41","target":"graph","created_at":"2026-07-05T10:56:32Z","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/2402.07033/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) with the Mixture-of-Experts (MoE) architectures have shown promising performance on various tasks. However, due to the huge model sizes, running them in resource-constrained environments where the GPU memory is not abundant is challenging. Some existing systems propose to use CPU resources to solve that, but they either suffer from the significant overhead of frequently moving data between CPU and GPU, or fail to consider distinct characteristics of CPUs and GPUs. This paper proposes Fiddler, a resource-efficient inference system for MoE models with limited GPU res","authors_text":"Baris Kasikci, Kan Zhu, Keisuke Kamahori, Tian Tang, Yile Gu","cross_cats":["cs.AI","cs.DC","cs.OS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-10T19:54:08Z","title":"Fiddler: CPU-GPU Orchestration for Fast Inference of Mixture-of-Experts Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.07033","kind":"arxiv","version":3},"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:f585e96439dc969d38f9e43ac346c7a284bf8b044243305f69aa720de3a47867","target":"record","created_at":"2026-07-05T10:56:32Z","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":"927c4391f7c4feddc73527dd7c9b06690c3c01825dc9b4bb1320c4ff42882f93","cross_cats_sorted":["cs.AI","cs.DC","cs.OS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-10T19:54:08Z","title_canon_sha256":"6e0bfbfa6b733e822383d513bab3bf37f19cf54a980a21a67d1975d99a3fe56e"},"schema_version":"1.0","source":{"id":"2402.07033","kind":"arxiv","version":3}},"canonical_sha256":"e4e018fa61d2ecccf82b07d302a82bb78a9874b236308717384d239ca1e962ac","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e4e018fa61d2ecccf82b07d302a82bb78a9874b236308717384d239ca1e962ac","first_computed_at":"2026-07-05T10:56:32.150676Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:56:32.150676Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oSFUapgBMfl9iA56+59OMVH3jn61nmiu779vVy4r9gX71oo1D+yfd1cfnb3gFZplGrnEkcOtcMzGPlfnb8yBAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:56:32.151165Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.07033","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f585e96439dc969d38f9e43ac346c7a284bf8b044243305f69aa720de3a47867","sha256:7c85be5feb07f68fe73ac6dc381e9e60e68605576e1cc6ba6968d9a7617fba41"],"state_sha256":"16a1ea59a5b1bd61895b679a44a65e61ec2ab83a4599870e108ad596146b7407"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JmgF/28iJSdYHGpJlCxRIMojXttuEhdMnF0j6yW08rTgemxIJe+9NJJ6Soy4GNGju1MiXJf07Bono3ypYqhWAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T21:00:59.475467Z","bundle_sha256":"cc6da994aa205fa85bcbab6e8948fac4da0991dc3c7f1a7dbdd67219e511ff5a"}}