{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:2DZYQWNB3UDGUNMC65OMVQMZJX","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":"80e3f4355f564ab92df021a937952999983ac36475c018970e1febdaa0c380ce","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-11-09T18:50:38Z","title_canon_sha256":"c5f690119287e5cb9ae5d5a79ad9e824a129162c7f3ee9d5d395416b65508654"},"schema_version":"1.0","source":{"id":"2211.05102","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.05102","created_at":"2026-07-05T05:14:45Z"},{"alias_kind":"arxiv_version","alias_value":"2211.05102v1","created_at":"2026-07-05T05:14:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.05102","created_at":"2026-07-05T05:14:45Z"},{"alias_kind":"pith_short_12","alias_value":"2DZYQWNB3UDG","created_at":"2026-07-05T05:14:45Z"},{"alias_kind":"pith_short_16","alias_value":"2DZYQWNB3UDGUNMC","created_at":"2026-07-05T05:14:45Z"},{"alias_kind":"pith_short_8","alias_value":"2DZYQWNB","created_at":"2026-07-05T05:14:45Z"}],"graph_snapshots":[{"event_id":"sha256:e7f533753373a85f5c5746e3b2a94d8477b4146b60a40219668ed8ce89ca1d37","target":"graph","created_at":"2026-07-05T05:14:45Z","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/2211.05102/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study the problem of efficient generative inference for Transformer models, in one of its most challenging settings: large deep models, with tight latency targets and long sequence lengths. Better understanding of the engineering tradeoffs for inference for large Transformer-based models is important as use cases of these models are growing rapidly throughout application areas. We develop a simple analytical model for inference efficiency to select the best multi-dimensional partitioning techniques optimized for TPU v4 slices based on the application requirements. We combine these with a su","authors_text":"Aakanksha Chowdhery, Anselm Levskaya, Jacob Devlin, James Bradbury, Jeff Dean, Jonathan Heek, Kefan Xiao, Reiner Pope, Shivani Agrawal, Sholto Douglas","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-11-09T18:50:38Z","title":"Efficiently Scaling Transformer Inference"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.05102","kind":"arxiv","version":1},"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:b10c731243cecd68c27999d7019f9a8e14d98c01ceb31eb59cb5b4896bac3896","target":"record","created_at":"2026-07-05T05:14:45Z","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":"80e3f4355f564ab92df021a937952999983ac36475c018970e1febdaa0c380ce","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-11-09T18:50:38Z","title_canon_sha256":"c5f690119287e5cb9ae5d5a79ad9e824a129162c7f3ee9d5d395416b65508654"},"schema_version":"1.0","source":{"id":"2211.05102","kind":"arxiv","version":1}},"canonical_sha256":"d0f38859a1dd066a3582f75ccac1994df35a3177c515a19903a8898ec51aec91","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d0f38859a1dd066a3582f75ccac1994df35a3177c515a19903a8898ec51aec91","first_computed_at":"2026-07-05T05:14:45.760175Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:14:45.760175Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DuBY+IWE0oDj+ONgKTB4QVEh9IUdh0t84UA882b4bMKbPFzFRwi6EjWjX8jvhLUgCKqdp/4K9gyPqEd6S2CjDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:14:45.760670Z","signed_message":"canonical_sha256_bytes"},"source_id":"2211.05102","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b10c731243cecd68c27999d7019f9a8e14d98c01ceb31eb59cb5b4896bac3896","sha256:e7f533753373a85f5c5746e3b2a94d8477b4146b60a40219668ed8ce89ca1d37"],"state_sha256":"b9593aa2cc7325a01849a806bfc5baacbb503e9cf906dc8d2d210ec5fe3adbcc"}