{"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/efficientqat-efficient-quantization-aware","title":"EfficientQAT: Efficient Quantization-Aware Training for Large Language Models","arxiv_id":"2407.11062","date":"2024-07-10","proceeding":null,"authors":["Mengzhao Chen","Wenqi Shao","Peng Xu","Jiahao Wang","Peng Gao","Kaipeng Zhang","Ping Luo"],"abstract":"Large language models (LLMs) are crucial in modern natural language processing and artificial intelligence. However, they face challenges in managing their significant memory requirements. Although quantization-aware training (QAT) offers a solution by reducing memory consumption through low-bit representations with minimal accuracy loss, it is impractical due to substantial training resources. To address this, we propose Efficient Quantization-Aware Training (EfficientQAT), a more feasible QAT algorithm. EfficientQAT involves two consecutive phases: Block-wise training of all parameters (Block-AP) and end-to-end training of quantization parameters (E2E-QP). To the best of our knowledge, Block-AP is the first method to enable direct training of all parameters in a block-wise manner, reducing accuracy loss in low-bit scenarios by enhancing the solution space during optimization. E2E-QP then trains only the quantization parameters (step sizes) end-to-end, further improving the performance of quantized models by considering interactions among all sub-modules. Extensive experiments demonstrate that EfficientQAT outperforms previous quantization methods across a range of models, including base LLMs, instruction-tuned LLMs, and multimodal LLMs, with scales from 7B to 70B parameters at various quantization bits. For instance, EfficientQAT obtains a 2-bit Llama-2-70B model on a single A100-80GB GPU in 41 hours, with less than 3 points accuracy degradation compared to the full precision (69.48 vs. 72.41). Code is available at https://github.com/OpenGVLab/EfficientQAT.","url_abs":"https://arxiv.org/abs/2407.11062v3","url_pdf":"https://arxiv.org/pdf/2407.11062v3.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":"efficientqat-efficient-quantization-aware","repo_url":"https://github.com/opengvlab/efficientqat","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":null,"task_name":"GPU"},{"task_slug":"quantization","task_name":"Quantization"}],"methods":[{"method_slug":"base","method_name":"BASE"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2407.11062","atlas_url":"https://app.syntology.ai/?focus=2407.11062","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.11062"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/opengvlab/efficientqat","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":1,"ran_draft_wrong":2,"unverified":6},"by_repo_kind":{"official":{"samples":9,"ran":3,"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":0,"samples":[{"code_sha256_prefix":"4ac3f836e543e81c","entry":"ampscaler_get_grad_norm","repo":"opengvlab/efficientqat","repo_kind":"official","path":"utils.py","file_url":"https://github.com/opengvlab/efficientqat/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4ac3f836e543e81c"}},{"code_sha256_prefix":"b5445674ab17410f","entry":"extract_alpaca_dataset","repo":"opengvlab/efficientqat","repo_kind":"official","path":"datautils_e2e.py","file_url":"https://github.com/opengvlab/efficientqat/blob/HEAD/datautils_e2e.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b5445674ab17410f"}},{"code_sha256_prefix":"89ce33341af66037","entry":"get_last_checkpoint","repo":"opengvlab/efficientqat","repo_kind":"official","path":"main_e2e_qp.py","file_url":"https://github.com/opengvlab/efficientqat/blob/HEAD/main_e2e_qp.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"89ce33341af66037"}},{"code_sha256_prefix":"87877d0c60858bff","entry":"create_logger","repo":"opengvlab/efficientqat","repo_kind":"official","path":"utils.py","file_url":"https://github.com/opengvlab/efficientqat/blob/HEAD/utils.py","link_basis":"plan_row","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"87877d0c60858bff"}},{"code_sha256_prefix":"2d9448699cce6e63","entry":"get_c4","repo":"opengvlab/efficientqat","repo_kind":"official","path":"datautils_block.py","file_url":"https://github.com/opengvlab/efficientqat/blob/HEAD/datautils_block.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2d9448699cce6e63"}},{"code_sha256_prefix":"a566c582d26ceb36","entry":"get_conv_template","repo":"opengvlab/efficientqat","repo_kind":"official","path":"deita_dataset/conversation.py","file_url":"https://github.com/opengvlab/efficientqat/blob/HEAD/deita_dataset/conversation.py","link_basis":"plan_row","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a566c582d26ceb36"}},{"code_sha256_prefix":"d26c6656a23451bd","entry":"get_redpajama","repo":"opengvlab/efficientqat","repo_kind":"official","path":"datautils_block.py","file_url":"https://github.com/opengvlab/efficientqat/blob/HEAD/datautils_block.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d26c6656a23451bd"}},{"code_sha256_prefix":"6d02281de8bfe304","entry":"get_wikitext2","repo":"opengvlab/efficientqat","repo_kind":"official","path":"datautils_block.py","file_url":"https://github.com/opengvlab/efficientqat/blob/HEAD/datautils_block.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6d02281de8bfe304"}},{"code_sha256_prefix":"a05847ca43287c3f","entry":"make_data_module","repo":"opengvlab/efficientqat","repo_kind":"official","path":"datautils_e2e.py","file_url":"https://github.com/opengvlab/efficientqat/blob/HEAD/datautils_e2e.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a05847ca43287c3f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}