{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:JPO2LRRJSVKAEOP7OQFGTFVMJC","short_pith_number":"pith:JPO2LRRJ","schema_version":"1.0","canonical_sha256":"4bdda5c62995540239ff740a6996ac4894bfd42ef07bb3b648216adbae22a2cf","source":{"kind":"arxiv","id":"2607.08930","version":1},"attestation_state":"computed","paper":{"title":"BlockServe: Block-Grained Continuous Batching for High-Throughput Diffusion LLM Serving","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ke Xu, Liangwei Yang, Philip S. Yu, Shanghao Li, Weizhi Zhang, Yuanjie Zhu, Zihe Song","submitted_at":"2026-07-09T20:48:08Z","abstract_excerpt":"Efficient serving of diffusion large language models (dLLMs) is hindered by convergence heterogeneity: when batching multiple requests, different sequences converge at different rates, causing faster requests to stall behind slower stragglers and introducing compute bubbles and tail latency. We present BlockServe, a continuous batching framework that integrates block-grained scheduling -- immediately evicting completed requests at block boundaries -- with mixed-state execution that extends dual cache and parallel decoding to heterogeneous batches via gather-scatter indexing. Furthermore, a com"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2607.08930","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-09T20:48:08Z","cross_cats_sorted":[],"title_canon_sha256":"a2f57b4ff33085a33cbcc11e686a92fc46e927f62fa75482e41446391933724b","abstract_canon_sha256":"60d523a32dbd67efe887ae4ea8a2a0546c46372adc0d94b3f584dd2d642f0556"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-13T00:17:27.795038Z","signature_b64":"o4sa+cxdjx1FdgEgnIx0f1d0Qh3Q8LvNl61E/UiJoH5ZxOjVtU+J7Z/8Syr7ymZvaIRugWZMQw+2keH59SalDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4bdda5c62995540239ff740a6996ac4894bfd42ef07bb3b648216adbae22a2cf","last_reissued_at":"2026-07-13T00:17:27.794046Z","signature_status":"signed_v1","first_computed_at":"2026-07-13T00:17:27.794046Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BlockServe: Block-Grained Continuous Batching for High-Throughput Diffusion LLM Serving","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ke Xu, Liangwei Yang, Philip S. Yu, Shanghao Li, Weizhi Zhang, Yuanjie Zhu, Zihe Song","submitted_at":"2026-07-09T20:48:08Z","abstract_excerpt":"Efficient serving of diffusion large language models (dLLMs) is hindered by convergence heterogeneity: when batching multiple requests, different sequences converge at different rates, causing faster requests to stall behind slower stragglers and introducing compute bubbles and tail latency. We present BlockServe, a continuous batching framework that integrates block-grained scheduling -- immediately evicting completed requests at block boundaries -- with mixed-state execution that extends dual cache and parallel decoding to heterogeneous batches via gather-scatter indexing. Furthermore, a com"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.08930","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/2607.08930/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2607.08930","created_at":"2026-07-13T00:17:27.794567+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.08930v1","created_at":"2026-07-13T00:17:27.794567+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.08930","created_at":"2026-07-13T00:17:27.794567+00:00"},{"alias_kind":"pith_short_12","alias_value":"JPO2LRRJSVKA","created_at":"2026-07-13T00:17:27.794567+00:00"},{"alias_kind":"pith_short_16","alias_value":"JPO2LRRJSVKAEOP7","created_at":"2026-07-13T00:17:27.794567+00:00"},{"alias_kind":"pith_short_8","alias_value":"JPO2LRRJ","created_at":"2026-07-13T00:17:27.794567+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JPO2LRRJSVKAEOP7OQFGTFVMJC","json":"https://pith.science/pith/JPO2LRRJSVKAEOP7OQFGTFVMJC.json","graph_json":"https://pith.science/api/pith-number/JPO2LRRJSVKAEOP7OQFGTFVMJC/graph.json","events_json":"https://pith.science/api/pith-number/JPO2LRRJSVKAEOP7OQFGTFVMJC/events.json","paper":"https://pith.science/paper/JPO2LRRJ"},"agent_actions":{"view_html":"https://pith.science/pith/JPO2LRRJSVKAEOP7OQFGTFVMJC","download_json":"https://pith.science/pith/JPO2LRRJSVKAEOP7OQFGTFVMJC.json","view_paper":"https://pith.science/paper/JPO2LRRJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.08930&json=true","fetch_graph":"https://pith.science/api/pith-number/JPO2LRRJSVKAEOP7OQFGTFVMJC/graph.json","fetch_events":"https://pith.science/api/pith-number/JPO2LRRJSVKAEOP7OQFGTFVMJC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JPO2LRRJSVKAEOP7OQFGTFVMJC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JPO2LRRJSVKAEOP7OQFGTFVMJC/action/storage_attestation","attest_author":"https://pith.science/pith/JPO2LRRJSVKAEOP7OQFGTFVMJC/action/author_attestation","sign_citation":"https://pith.science/pith/JPO2LRRJSVKAEOP7OQFGTFVMJC/action/citation_signature","submit_replication":"https://pith.science/pith/JPO2LRRJSVKAEOP7OQFGTFVMJC/action/replication_record"}},"created_at":"2026-07-13T00:17:27.794567+00:00","updated_at":"2026-07-13T00:17:27.794567+00:00"}