{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VPZ4ALLT4N4LXDVDL2TMO6F225","short_pith_number":"pith:VPZ4ALLT","schema_version":"1.0","canonical_sha256":"abf3c02d73e378bb8ea35ea6c778bad758c99fd0b4e0b4481c7e05c90b590e2e","source":{"kind":"arxiv","id":"2402.05628","version":1},"attestation_state":"computed","paper":{"title":"RepQuant: Towards Accurate Post-Training Quantization of Large Transformer Models via Scale Reparameterization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jing Zhang, Qingyi Gu, Xuewen Liu, Zhikai Li","submitted_at":"2024-02-08T12:35:41Z","abstract_excerpt":"Large transformer models have demonstrated remarkable success. Post-training quantization (PTQ), which requires only a small dataset for calibration and avoids end-to-end retraining, is a promising solution for compressing these large models. Regrettably, existing PTQ methods typically exhibit non-trivial performance loss. We find that the performance bottleneck stems from over-consideration of hardware compatibility in the quantization process, compelling them to reluctantly employ simple quantizers, albeit at the expense of accuracy. With the above insights, we propose RepQuant, a novel PTQ "},"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":"2402.05628","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-08T12:35:41Z","cross_cats_sorted":[],"title_canon_sha256":"2f667ea55c1783c29ea1e1e3285f3de72fcc905ac1be9bd43e4fcb327e8e7783","abstract_canon_sha256":"664255fc3357e7cfed00947bf7a8bcb7eb475a63427a8d0b2f022325fde411a1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:42:53.676384Z","signature_b64":"mqyY5GVSALqEgFGgBn9PkrQK+pTCJCCJRm8XymneVSdRpRqICWvwLS/El6+LF4GNP5DL303/fv5056hoIS/7CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"abf3c02d73e378bb8ea35ea6c778bad758c99fd0b4e0b4481c7e05c90b590e2e","last_reissued_at":"2026-07-05T07:42:53.675809Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:42:53.675809Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RepQuant: Towards Accurate Post-Training Quantization of Large Transformer Models via Scale Reparameterization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jing Zhang, Qingyi Gu, Xuewen Liu, Zhikai Li","submitted_at":"2024-02-08T12:35:41Z","abstract_excerpt":"Large transformer models have demonstrated remarkable success. Post-training quantization (PTQ), which requires only a small dataset for calibration and avoids end-to-end retraining, is a promising solution for compressing these large models. Regrettably, existing PTQ methods typically exhibit non-trivial performance loss. We find that the performance bottleneck stems from over-consideration of hardware compatibility in the quantization process, compelling them to reluctantly employ simple quantizers, albeit at the expense of accuracy. With the above insights, we propose RepQuant, a novel PTQ "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.05628","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/2402.05628/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":"2402.05628","created_at":"2026-07-05T07:42:53.675883+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.05628v1","created_at":"2026-07-05T07:42:53.675883+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.05628","created_at":"2026-07-05T07:42:53.675883+00:00"},{"alias_kind":"pith_short_12","alias_value":"VPZ4ALLT4N4L","created_at":"2026-07-05T07:42:53.675883+00:00"},{"alias_kind":"pith_short_16","alias_value":"VPZ4ALLT4N4LXDVD","created_at":"2026-07-05T07:42:53.675883+00:00"},{"alias_kind":"pith_short_8","alias_value":"VPZ4ALLT","created_at":"2026-07-05T07:42:53.675883+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/VPZ4ALLT4N4LXDVDL2TMO6F225","json":"https://pith.science/pith/VPZ4ALLT4N4LXDVDL2TMO6F225.json","graph_json":"https://pith.science/api/pith-number/VPZ4ALLT4N4LXDVDL2TMO6F225/graph.json","events_json":"https://pith.science/api/pith-number/VPZ4ALLT4N4LXDVDL2TMO6F225/events.json","paper":"https://pith.science/paper/VPZ4ALLT"},"agent_actions":{"view_html":"https://pith.science/pith/VPZ4ALLT4N4LXDVDL2TMO6F225","download_json":"https://pith.science/pith/VPZ4ALLT4N4LXDVDL2TMO6F225.json","view_paper":"https://pith.science/paper/VPZ4ALLT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.05628&json=true","fetch_graph":"https://pith.science/api/pith-number/VPZ4ALLT4N4LXDVDL2TMO6F225/graph.json","fetch_events":"https://pith.science/api/pith-number/VPZ4ALLT4N4LXDVDL2TMO6F225/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VPZ4ALLT4N4LXDVDL2TMO6F225/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VPZ4ALLT4N4LXDVDL2TMO6F225/action/storage_attestation","attest_author":"https://pith.science/pith/VPZ4ALLT4N4LXDVDL2TMO6F225/action/author_attestation","sign_citation":"https://pith.science/pith/VPZ4ALLT4N4LXDVDL2TMO6F225/action/citation_signature","submit_replication":"https://pith.science/pith/VPZ4ALLT4N4LXDVDL2TMO6F225/action/replication_record"}},"created_at":"2026-07-05T07:42:53.675883+00:00","updated_at":"2026-07-05T07:42:53.675883+00:00"}