{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:JNGYILPOGP4BBZNMJHGYVUGF5E","short_pith_number":"pith:JNGYILPO","schema_version":"1.0","canonical_sha256":"4b4d842dee33f810e5ac49cd8ad0c5e91191f83805fdb86313c6ae32e376ab34","source":{"kind":"arxiv","id":"2409.14887","version":4},"attestation_state":"computed","paper":{"title":"Deploying Open-Source Large Language Models: A performance Analysis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.PF","authors_text":"Dan Dutartre, Xavier Hinaut, Yannis Bendi-Ouis","submitted_at":"2024-09-23T10:35:57Z","abstract_excerpt":"Since the release of ChatGPT in November 2022, large language models (LLMs) have seen considerable success, including in the open-source community, with many open-weight models available. However, the requirements to deploy such a service are often unknown and difficult to evaluate in advance. To facilitate this process, we conducted numerous tests at the Centre Inria de l'Universit\\'e de Bordeaux. In this article, we propose a comparison of the performance of several models of different sizes (mainly Mistral and LLaMa) depending on the available GPUs, using vLLM, a Python library designed to "},"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":"2409.14887","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.PF","submitted_at":"2024-09-23T10:35:57Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"5bc07748a12b559b4ae35752c912b567aaf22afd997e49521c5adfa215e4df3c","abstract_canon_sha256":"93f9d1321223f808fe6680f29f3c91fce25ba04eeea08ee8f056c8e97a53294a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:20:05.175809Z","signature_b64":"ctiMMSIhyPdHHs64/54MwPoAilf0dlAFo6Rd799VYdJqL3b8jyKvp1W3ZkMSAnEkjp8FSV/EYr81p2TF1z5AAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4b4d842dee33f810e5ac49cd8ad0c5e91191f83805fdb86313c6ae32e376ab34","last_reissued_at":"2026-07-05T11:20:05.175291Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:20:05.175291Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deploying Open-Source Large Language Models: A performance Analysis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.PF","authors_text":"Dan Dutartre, Xavier Hinaut, Yannis Bendi-Ouis","submitted_at":"2024-09-23T10:35:57Z","abstract_excerpt":"Since the release of ChatGPT in November 2022, large language models (LLMs) have seen considerable success, including in the open-source community, with many open-weight models available. However, the requirements to deploy such a service are often unknown and difficult to evaluate in advance. To facilitate this process, we conducted numerous tests at the Centre Inria de l'Universit\\'e de Bordeaux. In this article, we propose a comparison of the performance of several models of different sizes (mainly Mistral and LLaMa) depending on the available GPUs, using vLLM, a Python library designed to "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.14887","kind":"arxiv","version":4},"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/2409.14887/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":"2409.14887","created_at":"2026-07-05T11:20:05.175361+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.14887v4","created_at":"2026-07-05T11:20:05.175361+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.14887","created_at":"2026-07-05T11:20:05.175361+00:00"},{"alias_kind":"pith_short_12","alias_value":"JNGYILPOGP4B","created_at":"2026-07-05T11:20:05.175361+00:00"},{"alias_kind":"pith_short_16","alias_value":"JNGYILPOGP4BBZNM","created_at":"2026-07-05T11:20:05.175361+00:00"},{"alias_kind":"pith_short_8","alias_value":"JNGYILPO","created_at":"2026-07-05T11:20:05.175361+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.05279","citing_title":"ReservoirChat: Interactive Documentation Enhanced with LLM and Knowledge Graph for ReservoirPy","ref_index":30,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JNGYILPOGP4BBZNMJHGYVUGF5E","json":"https://pith.science/pith/JNGYILPOGP4BBZNMJHGYVUGF5E.json","graph_json":"https://pith.science/api/pith-number/JNGYILPOGP4BBZNMJHGYVUGF5E/graph.json","events_json":"https://pith.science/api/pith-number/JNGYILPOGP4BBZNMJHGYVUGF5E/events.json","paper":"https://pith.science/paper/JNGYILPO"},"agent_actions":{"view_html":"https://pith.science/pith/JNGYILPOGP4BBZNMJHGYVUGF5E","download_json":"https://pith.science/pith/JNGYILPOGP4BBZNMJHGYVUGF5E.json","view_paper":"https://pith.science/paper/JNGYILPO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.14887&json=true","fetch_graph":"https://pith.science/api/pith-number/JNGYILPOGP4BBZNMJHGYVUGF5E/graph.json","fetch_events":"https://pith.science/api/pith-number/JNGYILPOGP4BBZNMJHGYVUGF5E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JNGYILPOGP4BBZNMJHGYVUGF5E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JNGYILPOGP4BBZNMJHGYVUGF5E/action/storage_attestation","attest_author":"https://pith.science/pith/JNGYILPOGP4BBZNMJHGYVUGF5E/action/author_attestation","sign_citation":"https://pith.science/pith/JNGYILPOGP4BBZNMJHGYVUGF5E/action/citation_signature","submit_replication":"https://pith.science/pith/JNGYILPOGP4BBZNMJHGYVUGF5E/action/replication_record"}},"created_at":"2026-07-05T11:20:05.175361+00:00","updated_at":"2026-07-05T11:20:05.175361+00:00"}