{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MDMR3FQC57FDDBUFCM6LXPYZ2D","short_pith_number":"pith:MDMR3FQC","schema_version":"1.0","canonical_sha256":"60d91d9602efca318685133cbbbf19d0d5eefb9a7e6833965b4ab7f279ba7606","source":{"kind":"arxiv","id":"2405.05465","version":2},"attestation_state":"computed","paper":{"title":"Vidur: A Large-Scale Simulation Framework For LLM Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Alexey Tumanov, Amey Agrawal, Ashish Panwar, Bhargav Gulavani, Jayashree Mohan, Nipun Kwatra, Nitin Kedia, Ramachandran Ramjee","submitted_at":"2024-05-08T23:42:13Z","abstract_excerpt":"Optimizing the deployment of Large language models (LLMs) is expensive today since it requires experimentally running an application workload against an LLM implementation while exploring large configuration space formed by system knobs such as parallelization strategies, batching techniques, and scheduling policies. To address this challenge, we present Vidur - a large-scale, high-fidelity, easily-extensible simulation framework for LLM inference performance. Vidur models the performance of LLM operators using a combination of experimental profiling and predictive modeling, and evaluates the "},"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":"2405.05465","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-08T23:42:13Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"08c7896e5c9889884f9c490971abc0082f26cd8523fc00b547d985c543cb3850","abstract_canon_sha256":"f122b7b59575a7bcd2a7257c03854a1fed98c0f2ff1b3b30df02373c29578bba"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:21:15.972640Z","signature_b64":"aX+x5VgNa7Fe8NC2tvRPuR8+Qfbpi0XNDmpB/DUPq0pywpmgRBIXl+1jGJFrQ024bl7uK7nQzH63qFrgzacsCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"60d91d9602efca318685133cbbbf19d0d5eefb9a7e6833965b4ab7f279ba7606","last_reissued_at":"2026-07-05T08:21:15.972119Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:21:15.972119Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Vidur: A Large-Scale Simulation Framework For LLM Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Alexey Tumanov, Amey Agrawal, Ashish Panwar, Bhargav Gulavani, Jayashree Mohan, Nipun Kwatra, Nitin Kedia, Ramachandran Ramjee","submitted_at":"2024-05-08T23:42:13Z","abstract_excerpt":"Optimizing the deployment of Large language models (LLMs) is expensive today since it requires experimentally running an application workload against an LLM implementation while exploring large configuration space formed by system knobs such as parallelization strategies, batching techniques, and scheduling policies. To address this challenge, we present Vidur - a large-scale, high-fidelity, easily-extensible simulation framework for LLM inference performance. Vidur models the performance of LLM operators using a combination of experimental profiling and predictive modeling, and evaluates the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.05465","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/2405.05465/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":"2405.05465","created_at":"2026-07-05T08:21:15.972181+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.05465v2","created_at":"2026-07-05T08:21:15.972181+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.05465","created_at":"2026-07-05T08:21:15.972181+00:00"},{"alias_kind":"pith_short_12","alias_value":"MDMR3FQC57FD","created_at":"2026-07-05T08:21:15.972181+00:00"},{"alias_kind":"pith_short_16","alias_value":"MDMR3FQC57FDDBUF","created_at":"2026-07-05T08:21:15.972181+00:00"},{"alias_kind":"pith_short_8","alias_value":"MDMR3FQC","created_at":"2026-07-05T08:21:15.972181+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.17949","citing_title":"RouteBalance: Fused Model Routing and Load Balancing for Heterogeneous LLM Serving","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.28302","citing_title":"How Far Can Disaggregation Go? A Design-Space Exploration of Attention-FFN Disaggregation for Efficient MoE LLM Serving","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2504.09775","citing_title":"MIST: A Co-Design Framework for Heterogeneous, Multi-Stage LLM Inference","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07985","citing_title":"Dooly: Configuration-Agnostic, Redundancy-Aware Profiling for LLM Inference Simulation","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17164","citing_title":"Charon: A Unified and Fine-Grained Simulator for Large-Scale LLM Training and Inference","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2601.14910","citing_title":"PipeWeave: Synergizing Analytical and Learning Models for Unified GPU Performance Prediction","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07985","citing_title":"Dooly: Configuration-Agnostic, Redundancy-Aware Profiling for LLM Inference Simulation","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MDMR3FQC57FDDBUFCM6LXPYZ2D","json":"https://pith.science/pith/MDMR3FQC57FDDBUFCM6LXPYZ2D.json","graph_json":"https://pith.science/api/pith-number/MDMR3FQC57FDDBUFCM6LXPYZ2D/graph.json","events_json":"https://pith.science/api/pith-number/MDMR3FQC57FDDBUFCM6LXPYZ2D/events.json","paper":"https://pith.science/paper/MDMR3FQC"},"agent_actions":{"view_html":"https://pith.science/pith/MDMR3FQC57FDDBUFCM6LXPYZ2D","download_json":"https://pith.science/pith/MDMR3FQC57FDDBUFCM6LXPYZ2D.json","view_paper":"https://pith.science/paper/MDMR3FQC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.05465&json=true","fetch_graph":"https://pith.science/api/pith-number/MDMR3FQC57FDDBUFCM6LXPYZ2D/graph.json","fetch_events":"https://pith.science/api/pith-number/MDMR3FQC57FDDBUFCM6LXPYZ2D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MDMR3FQC57FDDBUFCM6LXPYZ2D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MDMR3FQC57FDDBUFCM6LXPYZ2D/action/storage_attestation","attest_author":"https://pith.science/pith/MDMR3FQC57FDDBUFCM6LXPYZ2D/action/author_attestation","sign_citation":"https://pith.science/pith/MDMR3FQC57FDDBUFCM6LXPYZ2D/action/citation_signature","submit_replication":"https://pith.science/pith/MDMR3FQC57FDDBUFCM6LXPYZ2D/action/replication_record"}},"created_at":"2026-07-05T08:21:15.972181+00:00","updated_at":"2026-07-05T08:21:15.972181+00:00"}