{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:LQ67J327Y7FCBDZMKQVT7BBEEL","short_pith_number":"pith:LQ67J327","canonical_record":{"source":{"id":"2401.11181","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2024-01-20T09:43:36Z","cross_cats_sorted":[],"title_canon_sha256":"d3a72040bd1c172a4fa9938cb59d7622d79a8c6bce1e43194803f6b3f547bf47","abstract_canon_sha256":"ed8802b9c11510eed3006ebc8ab3f699a9e9a5e7c8e6a70baff78f38ef0e1172"},"schema_version":"1.0"},"canonical_sha256":"5c3df4ef5fc7ca208f2c542b3f842422f951e6ef191224a942afb6d32c5175a2","source":{"kind":"arxiv","id":"2401.11181","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.11181","created_at":"2026-07-05T07:35:46Z"},{"alias_kind":"arxiv_version","alias_value":"2401.11181v1","created_at":"2026-07-05T07:35:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.11181","created_at":"2026-07-05T07:35:46Z"},{"alias_kind":"pith_short_12","alias_value":"LQ67J327Y7FC","created_at":"2026-07-05T07:35:46Z"},{"alias_kind":"pith_short_16","alias_value":"LQ67J327Y7FCBDZM","created_at":"2026-07-05T07:35:46Z"},{"alias_kind":"pith_short_8","alias_value":"LQ67J327","created_at":"2026-07-05T07:35:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:LQ67J327Y7FCBDZMKQVT7BBEEL","target":"record","payload":{"canonical_record":{"source":{"id":"2401.11181","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2024-01-20T09:43:36Z","cross_cats_sorted":[],"title_canon_sha256":"d3a72040bd1c172a4fa9938cb59d7622d79a8c6bce1e43194803f6b3f547bf47","abstract_canon_sha256":"ed8802b9c11510eed3006ebc8ab3f699a9e9a5e7c8e6a70baff78f38ef0e1172"},"schema_version":"1.0"},"canonical_sha256":"5c3df4ef5fc7ca208f2c542b3f842422f951e6ef191224a942afb6d32c5175a2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:35:46.980169Z","signature_b64":"sIzWcUMqxpD9D9djknbwTYE6zs5d6eOn0RKUwdqsGFGSsaFwpQOw4fc6R/j7ybN8itSntSeEkOdm//ljDzBJCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5c3df4ef5fc7ca208f2c542b3f842422f951e6ef191224a942afb6d32c5175a2","last_reissued_at":"2026-07-05T07:35:46.979718Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:35:46.979718Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2401.11181","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":"2026-07-05T07:35:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4nf/guNb07LIhImUdZgMbekAO+9FDLyrk21klLSphsFkl1CPsPqiUHQ213vSXukiO9Ke/7cCkd69PrUSFbOVAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T17:10:51.508261Z"},"content_sha256":"4b063f5b737fbc686ec0b5dae4428cf9312b6c7fc6d0ecc50acd93750405b835","schema_version":"1.0","event_id":"sha256:4b063f5b737fbc686ec0b5dae4428cf9312b6c7fc6d0ecc50acd93750405b835"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:LQ67J327Y7FCBDZMKQVT7BBEEL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Inference without Interference: Disaggregate LLM Inference for Mixed Downstream Workloads","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DC","authors_text":"Chenxi Wang, Cunchen Hu, Hao Feng, Heyang Huang, Jiang Xu, Liangliang Xu, Ninghui Sun, Sa Wang, Shuang Chen, Xusheng Chen, Yizhou Shan, Yungang Bao","submitted_at":"2024-01-20T09:43:36Z","abstract_excerpt":"Transformer-based large language model (LLM) inference serving is now the backbone of many cloud services. LLM inference consists of a prefill phase and a decode phase. However, existing LLM deployment practices often overlook the distinct characteristics of these phases, leading to significant interference. To mitigate interference, our insight is to carefully schedule and group inference requests based on their characteristics. We realize this idea in TetriInfer through three pillars. First, it partitions prompts into fixed-size chunks so that the accelerator always runs close to its computa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.11181","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/2401.11181/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":"2026-07-05T07:35:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CaLgl+pS+xgBRKkSywsAi2vvL7+COTgiJEnGc7rPZlpQ6qpkyFcWuCFBWhwGo0QfKK2dwvcKrGxUMdiniznbAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T17:10:51.508857Z"},"content_sha256":"f2d77d33fafb27d48e1680a6e8fa0e5c30f3230bb2c79cb16737f391568661fe","schema_version":"1.0","event_id":"sha256:f2d77d33fafb27d48e1680a6e8fa0e5c30f3230bb2c79cb16737f391568661fe"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LQ67J327Y7FCBDZMKQVT7BBEEL/bundle.json","state_url":"https://pith.science/pith/LQ67J327Y7FCBDZMKQVT7BBEEL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LQ67J327Y7FCBDZMKQVT7BBEEL/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":"2026-08-07T17:10:51Z","links":{"resolver":"https://pith.science/pith/LQ67J327Y7FCBDZMKQVT7BBEEL","bundle":"https://pith.science/pith/LQ67J327Y7FCBDZMKQVT7BBEEL/bundle.json","state":"https://pith.science/pith/LQ67J327Y7FCBDZMKQVT7BBEEL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LQ67J327Y7FCBDZMKQVT7BBEEL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:LQ67J327Y7FCBDZMKQVT7BBEEL","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":"ed8802b9c11510eed3006ebc8ab3f699a9e9a5e7c8e6a70baff78f38ef0e1172","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2024-01-20T09:43:36Z","title_canon_sha256":"d3a72040bd1c172a4fa9938cb59d7622d79a8c6bce1e43194803f6b3f547bf47"},"schema_version":"1.0","source":{"id":"2401.11181","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.11181","created_at":"2026-07-05T07:35:46Z"},{"alias_kind":"arxiv_version","alias_value":"2401.11181v1","created_at":"2026-07-05T07:35:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.11181","created_at":"2026-07-05T07:35:46Z"},{"alias_kind":"pith_short_12","alias_value":"LQ67J327Y7FC","created_at":"2026-07-05T07:35:46Z"},{"alias_kind":"pith_short_16","alias_value":"LQ67J327Y7FCBDZM","created_at":"2026-07-05T07:35:46Z"},{"alias_kind":"pith_short_8","alias_value":"LQ67J327","created_at":"2026-07-05T07:35:46Z"}],"graph_snapshots":[{"event_id":"sha256:f2d77d33fafb27d48e1680a6e8fa0e5c30f3230bb2c79cb16737f391568661fe","target":"graph","created_at":"2026-07-05T07:35:46Z","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/2401.11181/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Transformer-based large language model (LLM) inference serving is now the backbone of many cloud services. LLM inference consists of a prefill phase and a decode phase. However, existing LLM deployment practices often overlook the distinct characteristics of these phases, leading to significant interference. To mitigate interference, our insight is to carefully schedule and group inference requests based on their characteristics. We realize this idea in TetriInfer through three pillars. First, it partitions prompts into fixed-size chunks so that the accelerator always runs close to its computa","authors_text":"Chenxi Wang, Cunchen Hu, Hao Feng, Heyang Huang, Jiang Xu, Liangliang Xu, Ninghui Sun, Sa Wang, Shuang Chen, Xusheng Chen, Yizhou Shan, Yungang Bao","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2024-01-20T09:43:36Z","title":"Inference without Interference: Disaggregate LLM Inference for Mixed Downstream Workloads"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.11181","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":"sha256:4b063f5b737fbc686ec0b5dae4428cf9312b6c7fc6d0ecc50acd93750405b835","target":"record","created_at":"2026-07-05T07:35:46Z","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":"ed8802b9c11510eed3006ebc8ab3f699a9e9a5e7c8e6a70baff78f38ef0e1172","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2024-01-20T09:43:36Z","title_canon_sha256":"d3a72040bd1c172a4fa9938cb59d7622d79a8c6bce1e43194803f6b3f547bf47"},"schema_version":"1.0","source":{"id":"2401.11181","kind":"arxiv","version":1}},"canonical_sha256":"5c3df4ef5fc7ca208f2c542b3f842422f951e6ef191224a942afb6d32c5175a2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5c3df4ef5fc7ca208f2c542b3f842422f951e6ef191224a942afb6d32c5175a2","first_computed_at":"2026-07-05T07:35:46.979718Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:35:46.979718Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sIzWcUMqxpD9D9djknbwTYE6zs5d6eOn0RKUwdqsGFGSsaFwpQOw4fc6R/j7ybN8itSntSeEkOdm//ljDzBJCg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:35:46.980169Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.11181","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4b063f5b737fbc686ec0b5dae4428cf9312b6c7fc6d0ecc50acd93750405b835","sha256:f2d77d33fafb27d48e1680a6e8fa0e5c30f3230bb2c79cb16737f391568661fe"],"state_sha256":"0b5735d61590a93bfa63afb388d0d6e844c6db8834ad76238e50c05d3cb355ff"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"J35TTgroeNRPV6lIwUhzKtEV8YAduw+H6PwlmfnDrIZpTDNlF7WyNUROPd1ekrsk+Yty8tLJmArtPPJxG7UVDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T17:10:51.512802Z","bundle_sha256":"e88dab76c7d4a5fa3271211139bfb21b6e337fb7af5960b38e36039a7a76288d"}}