{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:HQ5TUCISNEKQEIUX2VIGRLXBW3","short_pith_number":"pith:HQ5TUCIS","canonical_record":{"source":{"id":"2605.29639","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.OS","submitted_at":"2026-05-28T09:07:06Z","cross_cats_sorted":[],"title_canon_sha256":"dc562069102e87a8c04944fd1a8255145fd3b3b9a78bc88d35b39363919677b1","abstract_canon_sha256":"1abd42019c4a9b050e85ab6ec35499cf7bedb4d97c4f55d1eafc3a29b0e23132"},"schema_version":"1.0"},"canonical_sha256":"3c3b3a09126915022297d55068aee1b6d0221239ec601df09584c948c1d97f18","source":{"kind":"arxiv","id":"2605.29639","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.29639","created_at":"2026-05-29T01:05:52Z"},{"alias_kind":"arxiv_version","alias_value":"2605.29639v1","created_at":"2026-05-29T01:05:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.29639","created_at":"2026-05-29T01:05:52Z"},{"alias_kind":"pith_short_12","alias_value":"HQ5TUCISNEKQ","created_at":"2026-05-29T01:05:52Z"},{"alias_kind":"pith_short_16","alias_value":"HQ5TUCISNEKQEIUX","created_at":"2026-05-29T01:05:52Z"},{"alias_kind":"pith_short_8","alias_value":"HQ5TUCIS","created_at":"2026-05-29T01:05:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:HQ5TUCISNEKQEIUX2VIGRLXBW3","target":"record","payload":{"canonical_record":{"source":{"id":"2605.29639","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.OS","submitted_at":"2026-05-28T09:07:06Z","cross_cats_sorted":[],"title_canon_sha256":"dc562069102e87a8c04944fd1a8255145fd3b3b9a78bc88d35b39363919677b1","abstract_canon_sha256":"1abd42019c4a9b050e85ab6ec35499cf7bedb4d97c4f55d1eafc3a29b0e23132"},"schema_version":"1.0"},"canonical_sha256":"3c3b3a09126915022297d55068aee1b6d0221239ec601df09584c948c1d97f18","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T01:05:52.509115Z","signature_b64":"9tK1jJdNnoqGtY4iW/5BLVXovwulnQ5w4e80B7vfMCCSlrhpphZs5GuoYoOY/9xF0I4pgxVjuzByWhSk9diJBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3c3b3a09126915022297d55068aee1b6d0221239ec601df09584c948c1d97f18","last_reissued_at":"2026-05-29T01:05:52.508299Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T01:05:52.508299Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.29639","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-29T01:05:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JnSSQ97GvY0XrJsIBNt+DBcCYhMElgVVuZni7OUVdCJLPiNMJ9qRCzurkzFiQflHfUADISouKkzi+6xRa00xBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T02:12:54.906013Z"},"content_sha256":"e9cbcefd450a69421c70e7009351c32ed625bae2831c589c763d48e1ffeaf778","schema_version":"1.0","event_id":"sha256:e9cbcefd450a69421c70e7009351c32ed625bae2831c589c763d48e1ffeaf778"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:HQ5TUCISNEKQEIUX2VIGRLXBW3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"RTP-LLM: High-Performance Alibaba LLM Inference Engine","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.OS","authors_text":"Bo Cai, Boyu Tan, Chi Zhang, Guiyang Huang, Guoding Li, Hanbo Sun, Jianning Zhang, Jiarui Guo, Juncheng Yin, Kan Liu, Lin Qu, Lin Yang, Lu Chen, Na He, Nan Wang, Silu Zhou, Tao Lan, Tong Yang, Wei Zhang, Wending Bao, Xinfei Shi, Xi Yang, Xiyu Wang, Yaxin Yu, Yinghao Yu, Yuxing Yuan, Zechao Zhang, Zetao Hu, Zongwei Lv","submitted_at":"2026-05-28T09:07:06Z","abstract_excerpt":"Large Language Models (LLMs) have revolutionized AI applications, but deploying them at scale presents significant challenges. We present RTP-LLM, a high-performance inference engine for industrial-scale LLM deployment, successfully deployed across Alibaba Group serving over 100 million users. RTP-LLM addresses fundamental bottlenecks through integrated design. It optimizes model loading via file-order-driven I/O and parallel I/O-communication overlapping. The Prefill-Decode Disaggregation architecture decouples compute-intensive prefill from memory-bound decode phases, combined with hierarchi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.29639","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/2605.29639/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":"2026-05-29T01:05:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"46CLPs8aDXSu6oPRRtc1EG2OE8gmS9T8J5+GewUOuahW5kUPOa7PBRPorGXm5afRzjkpKXYnEENar+tLAXf7Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T02:12:54.906757Z"},"content_sha256":"0b9b4d11a1ed3737c98255623e3395818aeaecb471ba267de9f1a2ad0c828242","schema_version":"1.0","event_id":"sha256:0b9b4d11a1ed3737c98255623e3395818aeaecb471ba267de9f1a2ad0c828242"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HQ5TUCISNEKQEIUX2VIGRLXBW3/bundle.json","state_url":"https://pith.science/pith/HQ5TUCISNEKQEIUX2VIGRLXBW3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HQ5TUCISNEKQEIUX2VIGRLXBW3/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":"2026-06-01T02:12:54Z","links":{"resolver":"https://pith.science/pith/HQ5TUCISNEKQEIUX2VIGRLXBW3","bundle":"https://pith.science/pith/HQ5TUCISNEKQEIUX2VIGRLXBW3/bundle.json","state":"https://pith.science/pith/HQ5TUCISNEKQEIUX2VIGRLXBW3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HQ5TUCISNEKQEIUX2VIGRLXBW3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:HQ5TUCISNEKQEIUX2VIGRLXBW3","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":"1abd42019c4a9b050e85ab6ec35499cf7bedb4d97c4f55d1eafc3a29b0e23132","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.OS","submitted_at":"2026-05-28T09:07:06Z","title_canon_sha256":"dc562069102e87a8c04944fd1a8255145fd3b3b9a78bc88d35b39363919677b1"},"schema_version":"1.0","source":{"id":"2605.29639","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.29639","created_at":"2026-05-29T01:05:52Z"},{"alias_kind":"arxiv_version","alias_value":"2605.29639v1","created_at":"2026-05-29T01:05:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.29639","created_at":"2026-05-29T01:05:52Z"},{"alias_kind":"pith_short_12","alias_value":"HQ5TUCISNEKQ","created_at":"2026-05-29T01:05:52Z"},{"alias_kind":"pith_short_16","alias_value":"HQ5TUCISNEKQEIUX","created_at":"2026-05-29T01:05:52Z"},{"alias_kind":"pith_short_8","alias_value":"HQ5TUCIS","created_at":"2026-05-29T01:05:52Z"}],"graph_snapshots":[{"event_id":"sha256:0b9b4d11a1ed3737c98255623e3395818aeaecb471ba267de9f1a2ad0c828242","target":"graph","created_at":"2026-05-29T01:05:52Z","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/2605.29639/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) have revolutionized AI applications, but deploying them at scale presents significant challenges. We present RTP-LLM, a high-performance inference engine for industrial-scale LLM deployment, successfully deployed across Alibaba Group serving over 100 million users. RTP-LLM addresses fundamental bottlenecks through integrated design. It optimizes model loading via file-order-driven I/O and parallel I/O-communication overlapping. The Prefill-Decode Disaggregation architecture decouples compute-intensive prefill from memory-bound decode phases, combined with hierarchi","authors_text":"Bo Cai, Boyu Tan, Chi Zhang, Guiyang Huang, Guoding Li, Hanbo Sun, Jianning Zhang, Jiarui Guo, Juncheng Yin, Kan Liu, Lin Qu, Lin Yang, Lu Chen, Na He, Nan Wang, Silu Zhou, Tao Lan, Tong Yang, Wei Zhang, Wending Bao, Xinfei Shi, Xi Yang, Xiyu Wang, Yaxin Yu, Yinghao Yu, Yuxing Yuan, Zechao Zhang, Zetao Hu, Zongwei Lv","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.OS","submitted_at":"2026-05-28T09:07:06Z","title":"RTP-LLM: High-Performance Alibaba LLM Inference Engine"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.29639","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:e9cbcefd450a69421c70e7009351c32ed625bae2831c589c763d48e1ffeaf778","target":"record","created_at":"2026-05-29T01:05:52Z","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":"1abd42019c4a9b050e85ab6ec35499cf7bedb4d97c4f55d1eafc3a29b0e23132","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.OS","submitted_at":"2026-05-28T09:07:06Z","title_canon_sha256":"dc562069102e87a8c04944fd1a8255145fd3b3b9a78bc88d35b39363919677b1"},"schema_version":"1.0","source":{"id":"2605.29639","kind":"arxiv","version":1}},"canonical_sha256":"3c3b3a09126915022297d55068aee1b6d0221239ec601df09584c948c1d97f18","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3c3b3a09126915022297d55068aee1b6d0221239ec601df09584c948c1d97f18","first_computed_at":"2026-05-29T01:05:52.508299Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-29T01:05:52.508299Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9tK1jJdNnoqGtY4iW/5BLVXovwulnQ5w4e80B7vfMCCSlrhpphZs5GuoYoOY/9xF0I4pgxVjuzByWhSk9diJBA==","signature_status":"signed_v1","signed_at":"2026-05-29T01:05:52.509115Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.29639","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e9cbcefd450a69421c70e7009351c32ed625bae2831c589c763d48e1ffeaf778","sha256:0b9b4d11a1ed3737c98255623e3395818aeaecb471ba267de9f1a2ad0c828242"],"state_sha256":"570df2eaab2e7f91f95e1d51203e0e61470f0faa5a454d5ecae41fdf1d247ad9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JMoXEPSrQXsikiBjncI9cRSRJak5B5e9q/2yxB5f3tdSbCVGp9leisOTwW3NxlLHaFm6+vJiX7pCMMeB8ulGDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T02:12:54.911326Z","bundle_sha256":"44bc0ae691f274212077d6a3fb6731954473dd54873fdf8853f76446b04819d4"}}