{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:I3OC3PME3KZDIMB7PB725N65PV","short_pith_number":"pith:I3OC3PME","schema_version":"1.0","canonical_sha256":"46dc2dbd84dab234303f787faeb7dd7d697fa37536c69a0fa66d965c16025b16","source":{"kind":"arxiv","id":"2402.01799","version":2},"attestation_state":"computed","paper":{"title":"Faster and Lighter LLMs: A Survey on Current Challenges and Way Forward","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Arnav Chavan, Deepak Gupta, M\\'erouane Debbah, Raghav Magazine, Shubham Kushwaha","submitted_at":"2024-02-02T06:29:34Z","abstract_excerpt":"Despite the impressive performance of LLMs, their widespread adoption faces challenges due to substantial computational and memory requirements during inference. Recent advancements in model compression and system-level optimization methods aim to enhance LLM inference. This survey offers an overview of these methods, emphasizing recent developments. Through experiments on LLaMA(/2)-7B, we evaluate various compression techniques, providing practical insights for efficient LLM deployment in a unified setting. The empirical analysis on LLaMA(/2)-7B highlights the effectiveness of these methods. "},"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":"2402.01799","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-02T06:29:34Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"b6d80a789bd9f4f039b235dc65aa5164f1f11525a269054a22adc927492b4493","abstract_canon_sha256":"d49c0cd5892de1a3b987ea2e7bccd30fb8a39f59c312d8043a4ae7017116f9af"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:11:23.281207Z","signature_b64":"g+cXI3sCL/uEL6G6wmdTT/Jtl/av6zvY6P6yBtg7Onqu9DqVeDxisRP/upTkqZLZ8kOFhoe3qu5SO2yd/RG7DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"46dc2dbd84dab234303f787faeb7dd7d697fa37536c69a0fa66d965c16025b16","last_reissued_at":"2026-07-05T08:11:23.280751Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:11:23.280751Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Faster and Lighter LLMs: A Survey on Current Challenges and Way Forward","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Arnav Chavan, Deepak Gupta, M\\'erouane Debbah, Raghav Magazine, Shubham Kushwaha","submitted_at":"2024-02-02T06:29:34Z","abstract_excerpt":"Despite the impressive performance of LLMs, their widespread adoption faces challenges due to substantial computational and memory requirements during inference. Recent advancements in model compression and system-level optimization methods aim to enhance LLM inference. This survey offers an overview of these methods, emphasizing recent developments. Through experiments on LLaMA(/2)-7B, we evaluate various compression techniques, providing practical insights for efficient LLM deployment in a unified setting. The empirical analysis on LLaMA(/2)-7B highlights the effectiveness of these methods. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.01799","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/2402.01799/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":"2402.01799","created_at":"2026-07-05T08:11:23.280806+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.01799v2","created_at":"2026-07-05T08:11:23.280806+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.01799","created_at":"2026-07-05T08:11:23.280806+00:00"},{"alias_kind":"pith_short_12","alias_value":"I3OC3PME3KZD","created_at":"2026-07-05T08:11:23.280806+00:00"},{"alias_kind":"pith_short_16","alias_value":"I3OC3PME3KZDIMB7","created_at":"2026-07-05T08:11:23.280806+00:00"},{"alias_kind":"pith_short_8","alias_value":"I3OC3PME","created_at":"2026-07-05T08:11:23.280806+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.25704","citing_title":"PowLU: An Activation Function for Stable Pre-Training of LLMs","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2410.20791","citing_title":"From Cool Demos to Production-Ready FMware: Core Challenges and a Technology Roadmap","ref_index":30,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/I3OC3PME3KZDIMB7PB725N65PV","json":"https://pith.science/pith/I3OC3PME3KZDIMB7PB725N65PV.json","graph_json":"https://pith.science/api/pith-number/I3OC3PME3KZDIMB7PB725N65PV/graph.json","events_json":"https://pith.science/api/pith-number/I3OC3PME3KZDIMB7PB725N65PV/events.json","paper":"https://pith.science/paper/I3OC3PME"},"agent_actions":{"view_html":"https://pith.science/pith/I3OC3PME3KZDIMB7PB725N65PV","download_json":"https://pith.science/pith/I3OC3PME3KZDIMB7PB725N65PV.json","view_paper":"https://pith.science/paper/I3OC3PME","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.01799&json=true","fetch_graph":"https://pith.science/api/pith-number/I3OC3PME3KZDIMB7PB725N65PV/graph.json","fetch_events":"https://pith.science/api/pith-number/I3OC3PME3KZDIMB7PB725N65PV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/I3OC3PME3KZDIMB7PB725N65PV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/I3OC3PME3KZDIMB7PB725N65PV/action/storage_attestation","attest_author":"https://pith.science/pith/I3OC3PME3KZDIMB7PB725N65PV/action/author_attestation","sign_citation":"https://pith.science/pith/I3OC3PME3KZDIMB7PB725N65PV/action/citation_signature","submit_replication":"https://pith.science/pith/I3OC3PME3KZDIMB7PB725N65PV/action/replication_record"}},"created_at":"2026-07-05T08:11:23.280806+00:00","updated_at":"2026-07-05T08:11:23.280806+00:00"}