{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/lqer-low-rank-quantization-error","title":"LQER: Low-Rank Quantization Error Reconstruction for LLMs","arxiv_id":"2402.02446","date":"2024-02-04","proceeding":null,"authors":["Cheng Zhang","Jianyi Cheng","George A. Constantinides","Yiren Zhao"],"abstract":"Post-training quantization of Large Language Models (LLMs) is challenging. In this work, we introduce Low-rank Quantization Error Reduction (LQER), which combines quantization and low-rank approximation to recover the model capability. LQER leverages an activation-induced scale matrix to drive the singular value distribution of quantization error towards a desirable distribution, which enables nearly-lossless W4A8 quantization on various LLMs and downstream tasks without the need for knowledge distillation, grid search, or gradient-base iterative optimization. Unlike existing methods, the computation pattern of LQER eliminates the need for specialized Scatter and Gather processes to collect high-precision weights from irregular memory locations. Our W4A8 LLMs achieve near-lossless performance on six popular downstream tasks, while using 1.36$\\times$ fewer hardware resources than the leading state-of-the-art method. We open-source our framework at https://github.com/ChengZhang-98/lqer","url_abs":"https://arxiv.org/abs/2402.02446v3","url_pdf":"https://arxiv.org/pdf/2402.02446v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"lqer-low-rank-quantization-error","repo_url":"https://github.com/chengzhang-98/lqer","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"knowledge-distillation","task_name":"Knowledge Distillation"},{"task_slug":"quantization","task_name":"Quantization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2402.02446","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.02446"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/chengzhang-98/lqer","reach":{"status":"ok"}}],"summary":{"ran":6,"unverified":4},"by_repo_kind":{"official":{"samples":10,"ran":6,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":10,"samples":[{"code_sha256_prefix":"9eebde5b4aa47a22","entry":"collect_linear_weights","repo":"chengzhang-98/lqer","repo_kind":"official","path":"src/lqer/approximate/utils.py","file_url":"https://github.com/chengzhang-98/lqer/blob/HEAD/src/lqer/approximate/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9eebde5b4aa47a22"}},{"code_sha256_prefix":"4c37b3a06f65ec01","entry":"convert_none_to_str_na","repo":"chengzhang-98/lqer","repo_kind":"official","path":"src/lqer/utils.py","file_url":"https://github.com/chengzhang-98/lqer/blob/HEAD/src/lqer/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"4c37b3a06f65ec01"}},{"code_sha256_prefix":"a94b082c74445f99","entry":"convert_str_na_to_none","repo":"chengzhang-98/lqer","repo_kind":"official","path":"src/lqer/utils.py","file_url":"https://github.com/chengzhang-98/lqer/blob/HEAD/src/lqer/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a94b082c74445f99"}},{"code_sha256_prefix":"5f612508fe3af2e1","entry":"evaluate_perplexity","repo":"chengzhang-98/lqer","repo_kind":"official","path":"src/lqer/evaluate/evaluate_lm.py","file_url":"https://github.com/chengzhang-98/lqer/blob/HEAD/src/lqer/evaluate/evaluate_lm.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"5f612508fe3af2e1"}},{"code_sha256_prefix":"6221863a7f7985b2","entry":"get_logger","repo":"chengzhang-98/lqer","repo_kind":"official","path":"src/lqer/logging.py","file_url":"https://github.com/chengzhang-98/lqer/blob/HEAD/src/lqer/logging.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"6221863a7f7985b2"}},{"code_sha256_prefix":"0056989332540d95","entry":"load_config","repo":"chengzhang-98/lqer","repo_kind":"official","path":"src/lqer/utils.py","file_url":"https://github.com/chengzhang-98/lqer/blob/HEAD/src/lqer/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"0056989332540d95"}},{"code_sha256_prefix":"1275677ab4aec925","entry":"preprocess_data_module_slim_pajama_6b","repo":"chengzhang-98/lqer","repo_kind":"official","path":"src/lqer/datasets/slim_pajama.py","file_url":"https://github.com/chengzhang-98/lqer/blob/HEAD/src/lqer/datasets/slim_pajama.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1275677ab4aec925"}},{"code_sha256_prefix":"8d9b95e38531702b","entry":"preprocess_data_module_wikitext2","repo":"chengzhang-98/lqer","repo_kind":"official","path":"src/lqer/datasets/wikitext2.py","file_url":"https://github.com/chengzhang-98/lqer/blob/HEAD/src/lqer/datasets/wikitext2.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"8d9b95e38531702b"}},{"code_sha256_prefix":"97edeccc3fdc2cf3","entry":"run_evaluate_perplexity","repo":"chengzhang-98/lqer","repo_kind":"official","path":"src/lqer/runners.py","file_url":"https://github.com/chengzhang-98/lqer/blob/HEAD/src/lqer/runners.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"97edeccc3fdc2cf3"}},{"code_sha256_prefix":"4ac18e3bb2866bde","entry":"run_profiler","repo":"chengzhang-98/lqer","repo_kind":"official","path":"src/lqer/runners.py","file_url":"https://github.com/chengzhang-98/lqer/blob/HEAD/src/lqer/runners.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"4ac18e3bb2866bde"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}