{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:RC4DBL6A2OEX2GKZNOQ3IFQTDG","short_pith_number":"pith:RC4DBL6A","schema_version":"1.0","canonical_sha256":"88b830afc0d3897d19596ba1b41613199b340d812041d643c7a2ee568c9bb731","source":{"kind":"arxiv","id":"2506.19677","version":2},"attestation_state":"computed","paper":{"title":"Adaptive Request Scheduling for CodeLLM Serving with SLA Guarantees","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Ahmed E. Hassan, Boyuan Chen, Hanan Lutfiyya, Kishanthan Thangarajah, Shi Chang","submitted_at":"2025-06-24T14:44:33Z","abstract_excerpt":"Code Large Language Models (CodeLLMs) are increasingly integrated into modern software development workflows, yet efficiently serving them in resource-constrained, self-hosted environments remains a significant challenge. Existing LLM serving systems employs Continuous Batching for throughput improvement. However, they rely on static batch size configurations that cannot adapt to fluctuating request rates or heterogeneous workloads, leading to frequent SLA (Service Level Agreement) violations and unstable performance. In this study, We propose SABER, a dynamic batching strategy that predicts p"},"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":"2506.19677","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2025-06-24T14:44:33Z","cross_cats_sorted":[],"title_canon_sha256":"9942006789e254259209a69a79ac1210d5baae285cbb6064e577ad0d29196367","abstract_canon_sha256":"48a4319564d32db2b633b56b947cee119bed54292c38342b599671cd9c713c63"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:26:54.235956Z","signature_b64":"v2MvcosTpdVmcwCQ0B9i9CAV7q/NDU1/TGh+0cqaD4J69bvDoZFw9cGL5c7hhec3DTwhKVN98ULq2QANe5sqBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"88b830afc0d3897d19596ba1b41613199b340d812041d643c7a2ee568c9bb731","last_reissued_at":"2026-07-05T11:26:54.235457Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:26:54.235457Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adaptive Request Scheduling for CodeLLM Serving with SLA Guarantees","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Ahmed E. Hassan, Boyuan Chen, Hanan Lutfiyya, Kishanthan Thangarajah, Shi Chang","submitted_at":"2025-06-24T14:44:33Z","abstract_excerpt":"Code Large Language Models (CodeLLMs) are increasingly integrated into modern software development workflows, yet efficiently serving them in resource-constrained, self-hosted environments remains a significant challenge. Existing LLM serving systems employs Continuous Batching for throughput improvement. However, they rely on static batch size configurations that cannot adapt to fluctuating request rates or heterogeneous workloads, leading to frequent SLA (Service Level Agreement) violations and unstable performance. In this study, We propose SABER, a dynamic batching strategy that predicts p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.19677","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/2506.19677/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":"2506.19677","created_at":"2026-07-05T11:26:54.235531+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.19677v2","created_at":"2026-07-05T11:26:54.235531+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.19677","created_at":"2026-07-05T11:26:54.235531+00:00"},{"alias_kind":"pith_short_12","alias_value":"RC4DBL6A2OEX","created_at":"2026-07-05T11:26:54.235531+00:00"},{"alias_kind":"pith_short_16","alias_value":"RC4DBL6A2OEX2GKZ","created_at":"2026-07-05T11:26:54.235531+00:00"},{"alias_kind":"pith_short_8","alias_value":"RC4DBL6A","created_at":"2026-07-05T11:26:54.235531+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/RC4DBL6A2OEX2GKZNOQ3IFQTDG","json":"https://pith.science/pith/RC4DBL6A2OEX2GKZNOQ3IFQTDG.json","graph_json":"https://pith.science/api/pith-number/RC4DBL6A2OEX2GKZNOQ3IFQTDG/graph.json","events_json":"https://pith.science/api/pith-number/RC4DBL6A2OEX2GKZNOQ3IFQTDG/events.json","paper":"https://pith.science/paper/RC4DBL6A"},"agent_actions":{"view_html":"https://pith.science/pith/RC4DBL6A2OEX2GKZNOQ3IFQTDG","download_json":"https://pith.science/pith/RC4DBL6A2OEX2GKZNOQ3IFQTDG.json","view_paper":"https://pith.science/paper/RC4DBL6A","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.19677&json=true","fetch_graph":"https://pith.science/api/pith-number/RC4DBL6A2OEX2GKZNOQ3IFQTDG/graph.json","fetch_events":"https://pith.science/api/pith-number/RC4DBL6A2OEX2GKZNOQ3IFQTDG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RC4DBL6A2OEX2GKZNOQ3IFQTDG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RC4DBL6A2OEX2GKZNOQ3IFQTDG/action/storage_attestation","attest_author":"https://pith.science/pith/RC4DBL6A2OEX2GKZNOQ3IFQTDG/action/author_attestation","sign_citation":"https://pith.science/pith/RC4DBL6A2OEX2GKZNOQ3IFQTDG/action/citation_signature","submit_replication":"https://pith.science/pith/RC4DBL6A2OEX2GKZNOQ3IFQTDG/action/replication_record"}},"created_at":"2026-07-05T11:26:54.235531+00:00","updated_at":"2026-07-05T11:26:54.235531+00:00"}