{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:DR3U7MOI2ACNHKYZFSLE6LZ445","short_pith_number":"pith:DR3U7MOI","schema_version":"1.0","canonical_sha256":"1c774fb1c8d004d3ab192c964f2f3ce74e190d3124d6a6332a18e5dec03f7382","source":{"kind":"arxiv","id":"2308.13137","version":3},"attestation_state":"computed","paper":{"title":"OmniQuant: Omnidirectionally Calibrated Quantization for Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Kaipeng Zhang, Lirui Zhao, Mengzhao Chen, Peng Gao, Peng Xu, Ping Luo, Wenqi Shao, Yu Qiao, Zhaoyang Zhang, Zhiqian Li","submitted_at":"2023-08-25T02:28:35Z","abstract_excerpt":"Large language models (LLMs) have revolutionized natural language processing tasks. However, their practical deployment is hindered by their immense memory and computation requirements. Although recent post-training quantization (PTQ) methods are effective in reducing memory footprint and improving the computational efficiency of LLM, they hand-craft quantization parameters, leading to low performance, especially in extremely low-bit quantization. To tackle this issue, we introduce an Omnidirectionally calibrated Quantization (\\textbf{OmniQuant}) technique for LLMs, which achieves good perform"},"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":"2308.13137","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-08-25T02:28:35Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"4651835e4379a8de2609ce51a6837adde88eaba83903eb4c82a7c9226088ae98","abstract_canon_sha256":"5c49d6ff8fef946b6a1a57156a6c52830986758ffb8758ec88e6c684d9a17b1e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:56:51.569128Z","signature_b64":"aY/tJbId2SIoToG2k9hfErfcN77lZ7ctKVjZ7xD/wG7hzEGMORptKgj7YQtqj44UM9VmgJIq0eJdETjyfHvlBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1c774fb1c8d004d3ab192c964f2f3ce74e190d3124d6a6332a18e5dec03f7382","last_reissued_at":"2026-07-05T07:56:51.568775Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:56:51.568775Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OmniQuant: Omnidirectionally Calibrated Quantization for Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Kaipeng Zhang, Lirui Zhao, Mengzhao Chen, Peng Gao, Peng Xu, Ping Luo, Wenqi Shao, Yu Qiao, Zhaoyang Zhang, Zhiqian Li","submitted_at":"2023-08-25T02:28:35Z","abstract_excerpt":"Large language models (LLMs) have revolutionized natural language processing tasks. However, their practical deployment is hindered by their immense memory and computation requirements. Although recent post-training quantization (PTQ) methods are effective in reducing memory footprint and improving the computational efficiency of LLM, they hand-craft quantization parameters, leading to low performance, especially in extremely low-bit quantization. To tackle this issue, we introduce an Omnidirectionally calibrated Quantization (\\textbf{OmniQuant}) technique for LLMs, which achieves good perform"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.13137","kind":"arxiv","version":3},"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/2308.13137/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":"2308.13137","created_at":"2026-07-05T07:56:51.568832+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.13137v3","created_at":"2026-07-05T07:56:51.568832+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.13137","created_at":"2026-07-05T07:56:51.568832+00:00"},{"alias_kind":"pith_short_12","alias_value":"DR3U7MOI2ACN","created_at":"2026-07-05T07:56:51.568832+00:00"},{"alias_kind":"pith_short_16","alias_value":"DR3U7MOI2ACNHKYZ","created_at":"2026-07-05T07:56:51.568832+00:00"},{"alias_kind":"pith_short_8","alias_value":"DR3U7MOI","created_at":"2026-07-05T07:56:51.568832+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":33,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.23190","citing_title":"RAT: RunAnyThing via Fully Automated Environment Configuration","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2606.26587","citing_title":"SharQ: Bridging Activation Sparsity and FP4 Quantization for LLM Inference","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2606.23406","citing_title":"HyperQuant: A Rate-Distortion-Optimal Quantization Pipeline for Large Language and Diffusion Models","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2606.06547","citing_title":"FAIR-Calib: Frontier-Aware Instability-Reweighted Calibration for Post-Training Quantization of Diffusion Large Language Models","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2606.05429","citing_title":"Minimizing the Hidden Cost of Scales: Graph-Guided Ultra-Low-Bit Quantization for Large Language Models","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2606.04349","citing_title":"MorphoQuant: Modality-Aware Quantization for Omni-modal Large Language Models","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2606.02823","citing_title":"Qift: Shift-Friendly No-Zero W2 Post-Training Quantization for Rotated W2A4/KV4 LLM Inference","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08692","citing_title":"AAAC: Activation-Aware Adaptive Codebooks for 4-bit LLM Weight Quantization","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00573","citing_title":"LASER: Loss-Aware Singular-value Decomposition and Rank Allocation for Efficient Low-Precision Vision-Language Models","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00494","citing_title":"ProjQ: Project-and-Quantize for Adapter-Aware LLM Compression","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00535","citing_title":"DREAM-S: Speculative Decoding with Searchable Drafting and Target-Aware Refinement for Multimodal Generation","ref_index":67,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23078","citing_title":"GEMQ: Global Expert-Level Mixed-Precision Quantization for MoE LLMs","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2508.06974","citing_title":"Rethinking 1-bit Optimization Leveraging Pre-trained Large Language Models","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2511.06516","citing_title":"You Had One Job: Per-Task Quantization Using LLMs' Hidden Representations","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18800","citing_title":"Theory-optimal Quantization Based on Flatness","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17757","citing_title":"OSCAR: Offline Spectral Covariance-Aware Rotation for 2-bit KV Cache Quantization","ref_index":63,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19929","citing_title":"Breaking Modality Heterogeneity in Low-Bit Quantization for Large Vision-Language Models","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2509.09505","citing_title":"Combating the Memory Walls: Optimization Pathways for Long-Context Agentic LLM Inference","ref_index":65,"is_internal_anchor":false},{"citing_arxiv_id":"2405.16406","citing_title":"SpinQuant: LLM quantization with learned rotations","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13859","citing_title":"BiSpikCLM: A Spiking Language Model integrating Softmax-Free Spiking Attention and Spike-Aware Alignment Distillation","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13997","citing_title":"HodgeCover: Higher-Order Topological Coverage Drives Compression of Sparse Mixture-of-Experts","ref_index":59,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02501","citing_title":"ECG Foundation Models and Medical LLMs for Agentic Cardiovascular Intelligence at the Edge: A Review and Outlook","ref_index":97,"is_internal_anchor":false},{"citing_arxiv_id":"2604.03957","citing_title":"BWTA: Accurate and Efficient Binarized Transformer by Algorithm-Hardware Co-design","ref_index":60,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12464","citing_title":"Search Your Block Floating Point Scales!","ref_index":60,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04738","citing_title":"OSAQ: Outlier Self-Absorption for Accurate Low-bit LLM Quantization","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DR3U7MOI2ACNHKYZFSLE6LZ445","json":"https://pith.science/pith/DR3U7MOI2ACNHKYZFSLE6LZ445.json","graph_json":"https://pith.science/api/pith-number/DR3U7MOI2ACNHKYZFSLE6LZ445/graph.json","events_json":"https://pith.science/api/pith-number/DR3U7MOI2ACNHKYZFSLE6LZ445/events.json","paper":"https://pith.science/paper/DR3U7MOI"},"agent_actions":{"view_html":"https://pith.science/pith/DR3U7MOI2ACNHKYZFSLE6LZ445","download_json":"https://pith.science/pith/DR3U7MOI2ACNHKYZFSLE6LZ445.json","view_paper":"https://pith.science/paper/DR3U7MOI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.13137&json=true","fetch_graph":"https://pith.science/api/pith-number/DR3U7MOI2ACNHKYZFSLE6LZ445/graph.json","fetch_events":"https://pith.science/api/pith-number/DR3U7MOI2ACNHKYZFSLE6LZ445/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DR3U7MOI2ACNHKYZFSLE6LZ445/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DR3U7MOI2ACNHKYZFSLE6LZ445/action/storage_attestation","attest_author":"https://pith.science/pith/DR3U7MOI2ACNHKYZFSLE6LZ445/action/author_attestation","sign_citation":"https://pith.science/pith/DR3U7MOI2ACNHKYZFSLE6LZ445/action/citation_signature","submit_replication":"https://pith.science/pith/DR3U7MOI2ACNHKYZFSLE6LZ445/action/replication_record"}},"created_at":"2026-07-05T07:56:51.568832+00:00","updated_at":"2026-07-05T07:56:51.568832+00:00"}