{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:S6C3UL2EYHMAIO2JEGUHT6OX7V","short_pith_number":"pith:S6C3UL2E","canonical_record":{"source":{"id":"2407.02490","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-02T17:59:56Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"6969e27160195809c2f2ddb8d62c72718ff1a658dc396698a12c1209b8a0278c","abstract_canon_sha256":"e4b25a9d3000f6ec194507ac1bf1704dfd1de4d91703b81630066b8535e7a94f"},"schema_version":"1.0"},"canonical_sha256":"9785ba2f44c1d8043b4921a879f9d7fd65358f2e573b9f2a742c9eb389e38e69","source":{"kind":"arxiv","id":"2407.02490","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.02490","created_at":"2026-07-05T09:28:33Z"},{"alias_kind":"arxiv_version","alias_value":"2407.02490v2","created_at":"2026-07-05T09:28:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.02490","created_at":"2026-07-05T09:28:33Z"},{"alias_kind":"pith_short_12","alias_value":"S6C3UL2EYHMA","created_at":"2026-07-05T09:28:33Z"},{"alias_kind":"pith_short_16","alias_value":"S6C3UL2EYHMAIO2J","created_at":"2026-07-05T09:28:33Z"},{"alias_kind":"pith_short_8","alias_value":"S6C3UL2E","created_at":"2026-07-05T09:28:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:S6C3UL2EYHMAIO2JEGUHT6OX7V","target":"record","payload":{"canonical_record":{"source":{"id":"2407.02490","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-02T17:59:56Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"6969e27160195809c2f2ddb8d62c72718ff1a658dc396698a12c1209b8a0278c","abstract_canon_sha256":"e4b25a9d3000f6ec194507ac1bf1704dfd1de4d91703b81630066b8535e7a94f"},"schema_version":"1.0"},"canonical_sha256":"9785ba2f44c1d8043b4921a879f9d7fd65358f2e573b9f2a742c9eb389e38e69","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:28:33.211979Z","signature_b64":"R178uf+8J2uNdA2qkrT/ssRKwOIJkkniKyzqiFeMOK8yWeSurdWC2ojZt7Qxw1svWvSP2xm6MqzQKelmHOhhAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9785ba2f44c1d8043b4921a879f9d7fd65358f2e573b9f2a742c9eb389e38e69","last_reissued_at":"2026-07-05T09:28:33.211508Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:28:33.211508Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.02490","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:28:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tJGCDnlxcGyhHo2ahtttWV5e0vAyjEMhrSiekiE3jlAy1kh/SDg+hs3aCBRKgJZbVsETOnxlXlMvMlSsVLQYAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-19T02:00:48.669832Z"},"content_sha256":"b2891d070ffa04bc9745f92e8c6171b3d977c08c0c920aabf2265eb72444396f","schema_version":"1.0","event_id":"sha256:b2891d070ffa04bc9745f92e8c6171b3d977c08c0c920aabf2265eb72444396f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:S6C3UL2EYHMAIO2JEGUHT6OX7V","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MInference 1.0: Accelerating Pre-filling for Long-Context LLMs via Dynamic Sparse Attention","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Amir H. Abdi, Chengruidong Zhang, Chin-Yew Lin, Dongsheng Li, Huiqiang Jiang, Lili Qiu, Qianhui Wu, Surin Ahn, Xufang Luo, Yucheng Li, Yuqing Yang, Zhenhua Han","submitted_at":"2024-07-02T17:59:56Z","abstract_excerpt":"The computational challenges of Large Language Model (LLM) inference remain a significant barrier to their widespread deployment, especially as prompt lengths continue to increase. Due to the quadratic complexity of the attention computation, it takes 30 minutes for an 8B LLM to process a prompt of 1M tokens (i.e., the pre-filling stage) on a single A100 GPU. Existing methods for speeding up prefilling often fail to maintain acceptable accuracy or efficiency when applied to long-context LLMs. To address this gap, we introduce MInference (Milliontokens Inference), a sparse calculation method de"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.02490","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/2407.02490/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":"2026-07-05T09:28:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DLfQ2jYKVVe2xmRmsxmM1EKr67AVcnRtphA04BJ48XDF7WI05DBxnckk7utugz3psHllLrHpjswVkV8DtJoaAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-19T02:00:48.670206Z"},"content_sha256":"160523c0e922c6e362c4e238bcc665f5756f1838620f9625d520c56827341e5e","schema_version":"1.0","event_id":"sha256:160523c0e922c6e362c4e238bcc665f5756f1838620f9625d520c56827341e5e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/S6C3UL2EYHMAIO2JEGUHT6OX7V/bundle.json","state_url":"https://pith.science/pith/S6C3UL2EYHMAIO2JEGUHT6OX7V/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/S6C3UL2EYHMAIO2JEGUHT6OX7V/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":"2026-07-19T02:00:48Z","links":{"resolver":"https://pith.science/pith/S6C3UL2EYHMAIO2JEGUHT6OX7V","bundle":"https://pith.science/pith/S6C3UL2EYHMAIO2JEGUHT6OX7V/bundle.json","state":"https://pith.science/pith/S6C3UL2EYHMAIO2JEGUHT6OX7V/state.json","well_known_bundle":"https://pith.science/.well-known/pith/S6C3UL2EYHMAIO2JEGUHT6OX7V/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:S6C3UL2EYHMAIO2JEGUHT6OX7V","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":"e4b25a9d3000f6ec194507ac1bf1704dfd1de4d91703b81630066b8535e7a94f","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-02T17:59:56Z","title_canon_sha256":"6969e27160195809c2f2ddb8d62c72718ff1a658dc396698a12c1209b8a0278c"},"schema_version":"1.0","source":{"id":"2407.02490","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.02490","created_at":"2026-07-05T09:28:33Z"},{"alias_kind":"arxiv_version","alias_value":"2407.02490v2","created_at":"2026-07-05T09:28:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.02490","created_at":"2026-07-05T09:28:33Z"},{"alias_kind":"pith_short_12","alias_value":"S6C3UL2EYHMA","created_at":"2026-07-05T09:28:33Z"},{"alias_kind":"pith_short_16","alias_value":"S6C3UL2EYHMAIO2J","created_at":"2026-07-05T09:28:33Z"},{"alias_kind":"pith_short_8","alias_value":"S6C3UL2E","created_at":"2026-07-05T09:28:33Z"}],"graph_snapshots":[{"event_id":"sha256:160523c0e922c6e362c4e238bcc665f5756f1838620f9625d520c56827341e5e","target":"graph","created_at":"2026-07-05T09:28:33Z","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/2407.02490/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The computational challenges of Large Language Model (LLM) inference remain a significant barrier to their widespread deployment, especially as prompt lengths continue to increase. Due to the quadratic complexity of the attention computation, it takes 30 minutes for an 8B LLM to process a prompt of 1M tokens (i.e., the pre-filling stage) on a single A100 GPU. Existing methods for speeding up prefilling often fail to maintain acceptable accuracy or efficiency when applied to long-context LLMs. To address this gap, we introduce MInference (Milliontokens Inference), a sparse calculation method de","authors_text":"Amir H. Abdi, Chengruidong Zhang, Chin-Yew Lin, Dongsheng Li, Huiqiang Jiang, Lili Qiu, Qianhui Wu, Surin Ahn, Xufang Luo, Yucheng Li, Yuqing Yang, Zhenhua Han","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-02T17:59:56Z","title":"MInference 1.0: Accelerating Pre-filling for Long-Context LLMs via Dynamic Sparse Attention"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.02490","kind":"arxiv","version":2},"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:b2891d070ffa04bc9745f92e8c6171b3d977c08c0c920aabf2265eb72444396f","target":"record","created_at":"2026-07-05T09:28:33Z","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":"e4b25a9d3000f6ec194507ac1bf1704dfd1de4d91703b81630066b8535e7a94f","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-02T17:59:56Z","title_canon_sha256":"6969e27160195809c2f2ddb8d62c72718ff1a658dc396698a12c1209b8a0278c"},"schema_version":"1.0","source":{"id":"2407.02490","kind":"arxiv","version":2}},"canonical_sha256":"9785ba2f44c1d8043b4921a879f9d7fd65358f2e573b9f2a742c9eb389e38e69","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9785ba2f44c1d8043b4921a879f9d7fd65358f2e573b9f2a742c9eb389e38e69","first_computed_at":"2026-07-05T09:28:33.211508Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:28:33.211508Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"R178uf+8J2uNdA2qkrT/ssRKwOIJkkniKyzqiFeMOK8yWeSurdWC2ojZt7Qxw1svWvSP2xm6MqzQKelmHOhhAg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:28:33.211979Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.02490","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b2891d070ffa04bc9745f92e8c6171b3d977c08c0c920aabf2265eb72444396f","sha256:160523c0e922c6e362c4e238bcc665f5756f1838620f9625d520c56827341e5e"],"state_sha256":"2102e43f97adac657059b10a1419c5f2ea953c39bda94eb1ac00d7cb5e7befe0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wE93dtrMI/nbt16u35LapDqV7cGP/MHubJLh4NJRsQVNdsvyaqB9UafCw09AUe4muXNzrcBJ++cdCJJ1p7Y8DQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-19T02:00:48.672755Z","bundle_sha256":"70b9ad7f46c1452737325a5eca5da542416557b6f148823671d0e35341cabf05"}}