{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:7WGZ73QCFIKL7ZFVGFI4BBVTQU","short_pith_number":"pith:7WGZ73QC","canonical_record":{"source":{"id":"2311.01282","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-11-02T14:57:03Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"5340a46b1e848a11a216217434b1e1a0a9d7c4093b4a2593909a5383122dc57e","abstract_canon_sha256":"15313c3ef0ae48beb5212a25faf711fbff91b41f6ad020c5a94e9c0c712e1734"},"schema_version":"1.0"},"canonical_sha256":"fd8d9fee022a14bfe4b53151c086b3850d542f7e3b90c96bf8a122ad3bd6eece","source":{"kind":"arxiv","id":"2311.01282","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.01282","created_at":"2026-07-05T07:30:23Z"},{"alias_kind":"arxiv_version","alias_value":"2311.01282v4","created_at":"2026-07-05T07:30:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.01282","created_at":"2026-07-05T07:30:23Z"},{"alias_kind":"pith_short_12","alias_value":"7WGZ73QCFIKL","created_at":"2026-07-05T07:30:23Z"},{"alias_kind":"pith_short_16","alias_value":"7WGZ73QCFIKL7ZFV","created_at":"2026-07-05T07:30:23Z"},{"alias_kind":"pith_short_8","alias_value":"7WGZ73QC","created_at":"2026-07-05T07:30:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:7WGZ73QCFIKL7ZFVGFI4BBVTQU","target":"record","payload":{"canonical_record":{"source":{"id":"2311.01282","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-11-02T14:57:03Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"5340a46b1e848a11a216217434b1e1a0a9d7c4093b4a2593909a5383122dc57e","abstract_canon_sha256":"15313c3ef0ae48beb5212a25faf711fbff91b41f6ad020c5a94e9c0c712e1734"},"schema_version":"1.0"},"canonical_sha256":"fd8d9fee022a14bfe4b53151c086b3850d542f7e3b90c96bf8a122ad3bd6eece","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:30:23.645420Z","signature_b64":"Rs9ritozl5t89AUcdoVt2HmmBU4OY5Zwtrx6cEf/x/fko6kkcDBTCF2hTM8AbVoCqL5cTh5VGiY5y4/rCPZZAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fd8d9fee022a14bfe4b53151c086b3850d542f7e3b90c96bf8a122ad3bd6eece","last_reissued_at":"2026-07-05T07:30:23.644914Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:30:23.644914Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2311.01282","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:30:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jTBU/qH5JOH7Q6zwl9tOoN7eKr547EHCUWrd6rEhCfQOhVotR/KdbN81d2xhOSo10D/NNma1D7FbXfADSmsyCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T03:04:05.469359Z"},"content_sha256":"c92521dc6a78c63df3feee71d8379d51188971ea4fdbe239041a9e6ac38ce330","schema_version":"1.0","event_id":"sha256:c92521dc6a78c63df3feee71d8379d51188971ea4fdbe239041a9e6ac38ce330"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:7WGZ73QCFIKL7ZFVGFI4BBVTQU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"FlashDecoding++: Faster Large Language Model Inference on GPUs","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Guohao Dai, Jiaming Xu, Jun Liu, Kangdi Chen, Ke Hong, Qiuli Mao, Xiuhong Li, Yuhan Dong, Yu Wang","submitted_at":"2023-11-02T14:57:03Z","abstract_excerpt":"As the Large Language Model (LLM) becomes increasingly important in various domains. However, the following challenges still remain unsolved in accelerating LLM inference: (1) Synchronized partial softmax update. The softmax operation requires a synchronized update operation among each partial softmax result, leading to ~20% overheads for the attention computation in LLMs. (2) Under-utilized computation of flat GEMM. The shape of matrices performing GEMM in LLM inference is flat, leading to under-utilized computation and >50% performance loss after padding zeros in previous designs. (3) Perfor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.01282","kind":"arxiv","version":4},"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/2311.01282/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":"2026-07-05T07:30:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"auO81+zMf3k7TK6hg/+zGbXP3r3zu55K6cvfGLoPSGv7OkhaiSTclD+LrnYX4LcszZIygWQWP69C4LqudbnpAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T03:04:05.469875Z"},"content_sha256":"6f39cd44cc622d19b8d99d00ccf46a02f095cdcf2c56ac7cf8932975e397f50c","schema_version":"1.0","event_id":"sha256:6f39cd44cc622d19b8d99d00ccf46a02f095cdcf2c56ac7cf8932975e397f50c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7WGZ73QCFIKL7ZFVGFI4BBVTQU/bundle.json","state_url":"https://pith.science/pith/7WGZ73QCFIKL7ZFVGFI4BBVTQU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7WGZ73QCFIKL7ZFVGFI4BBVTQU/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":"2026-08-09T03:04:05Z","links":{"resolver":"https://pith.science/pith/7WGZ73QCFIKL7ZFVGFI4BBVTQU","bundle":"https://pith.science/pith/7WGZ73QCFIKL7ZFVGFI4BBVTQU/bundle.json","state":"https://pith.science/pith/7WGZ73QCFIKL7ZFVGFI4BBVTQU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7WGZ73QCFIKL7ZFVGFI4BBVTQU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:7WGZ73QCFIKL7ZFVGFI4BBVTQU","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":"15313c3ef0ae48beb5212a25faf711fbff91b41f6ad020c5a94e9c0c712e1734","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-11-02T14:57:03Z","title_canon_sha256":"5340a46b1e848a11a216217434b1e1a0a9d7c4093b4a2593909a5383122dc57e"},"schema_version":"1.0","source":{"id":"2311.01282","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.01282","created_at":"2026-07-05T07:30:23Z"},{"alias_kind":"arxiv_version","alias_value":"2311.01282v4","created_at":"2026-07-05T07:30:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.01282","created_at":"2026-07-05T07:30:23Z"},{"alias_kind":"pith_short_12","alias_value":"7WGZ73QCFIKL","created_at":"2026-07-05T07:30:23Z"},{"alias_kind":"pith_short_16","alias_value":"7WGZ73QCFIKL7ZFV","created_at":"2026-07-05T07:30:23Z"},{"alias_kind":"pith_short_8","alias_value":"7WGZ73QC","created_at":"2026-07-05T07:30:23Z"}],"graph_snapshots":[{"event_id":"sha256:6f39cd44cc622d19b8d99d00ccf46a02f095cdcf2c56ac7cf8932975e397f50c","target":"graph","created_at":"2026-07-05T07:30:23Z","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/2311.01282/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As the Large Language Model (LLM) becomes increasingly important in various domains. However, the following challenges still remain unsolved in accelerating LLM inference: (1) Synchronized partial softmax update. The softmax operation requires a synchronized update operation among each partial softmax result, leading to ~20% overheads for the attention computation in LLMs. (2) Under-utilized computation of flat GEMM. The shape of matrices performing GEMM in LLM inference is flat, leading to under-utilized computation and >50% performance loss after padding zeros in previous designs. (3) Perfor","authors_text":"Guohao Dai, Jiaming Xu, Jun Liu, Kangdi Chen, Ke Hong, Qiuli Mao, Xiuhong Li, Yuhan Dong, Yu Wang","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-11-02T14:57:03Z","title":"FlashDecoding++: Faster Large Language Model Inference on GPUs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.01282","kind":"arxiv","version":4},"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:c92521dc6a78c63df3feee71d8379d51188971ea4fdbe239041a9e6ac38ce330","target":"record","created_at":"2026-07-05T07:30:23Z","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":"15313c3ef0ae48beb5212a25faf711fbff91b41f6ad020c5a94e9c0c712e1734","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-11-02T14:57:03Z","title_canon_sha256":"5340a46b1e848a11a216217434b1e1a0a9d7c4093b4a2593909a5383122dc57e"},"schema_version":"1.0","source":{"id":"2311.01282","kind":"arxiv","version":4}},"canonical_sha256":"fd8d9fee022a14bfe4b53151c086b3850d542f7e3b90c96bf8a122ad3bd6eece","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fd8d9fee022a14bfe4b53151c086b3850d542f7e3b90c96bf8a122ad3bd6eece","first_computed_at":"2026-07-05T07:30:23.644914Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:30:23.644914Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Rs9ritozl5t89AUcdoVt2HmmBU4OY5Zwtrx6cEf/x/fko6kkcDBTCF2hTM8AbVoCqL5cTh5VGiY5y4/rCPZZAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:30:23.645420Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.01282","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c92521dc6a78c63df3feee71d8379d51188971ea4fdbe239041a9e6ac38ce330","sha256:6f39cd44cc622d19b8d99d00ccf46a02f095cdcf2c56ac7cf8932975e397f50c"],"state_sha256":"98a889a4597f44eab4436289dbd735329e56236c52fbb9dc9dbc6048d9eb0292"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2sfyWZfMKP7clR6D9sLhhWZicB/VM5iep2Jsst3GLlOXrwebAR6fZKIP88hdNoIltVPqYqCfgOj8IkAi1j4zBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T03:04:05.475452Z","bundle_sha256":"2c41f63857fb7f370c2db8fce4fe6847f9efb6ff3ae1bf55bfa64ae4a34a5900"}}