{"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/smoothquant-accurate-and-efficient-post","title":"SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models","arxiv_id":"2211.10438","date":"2022-11-18","proceeding":null,"authors":["Guangxuan Xiao","Ji Lin","Mickael Seznec","Hao Wu","Julien Demouth","Song Han"],"abstract":"Large language models (LLMs) show excellent performance but are compute- and memory-intensive. Quantization can reduce memory and accelerate inference. However, existing methods cannot maintain accuracy and hardware efficiency at the same time. We propose SmoothQuant, a training-free, accuracy-preserving, and general-purpose post-training quantization (PTQ) solution to enable 8-bit weight, 8-bit activation (W8A8) quantization for LLMs. Based on the fact that weights are easy to quantize while activations are not, SmoothQuant smooths the activation outliers by offline migrating the quantization difficulty from activations to weights with a mathematically equivalent transformation. SmoothQuant enables an INT8 quantization of both weights and activations for all the matrix multiplications in LLMs, including OPT, BLOOM, GLM, MT-NLG, Llama-1/2, Falcon, Mistral, and Mixtral models. We demonstrate up to 1.56x speedup and 2x memory reduction for LLMs with negligible loss in accuracy. SmoothQuant enables serving 530B LLM within a single node. Our work offers a turn-key solution that reduces hardware costs and democratizes LLMs. Code is available at https://github.com/mit-han-lab/smoothquant.","url_abs":"https://arxiv.org/abs/2211.10438v7","url_pdf":"https://arxiv.org/pdf/2211.10438v7.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":"smoothquant-accurate-and-efficient-post","repo_url":"https://github.com/mit-han-lab/smoothquant","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"smoothquant-accurate-and-efficient-post","repo_url":"https://github.com/BlinkDL/RWKV-LM","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"smoothquant-accurate-and-efficient-post","repo_url":"https://github.com/adlik/smoothquantplus","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"smoothquant-accurate-and-efficient-post","repo_url":"https://github.com/cornell-zhang/llm-datatypes","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"smoothquant-accurate-and-efficient-post","repo_url":"https://github.com/nvidia/tensorrt-llm","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"quantization","task_name":"Quantization"}],"methods":[{"method_slug":"bloom","method_name":"BLOOM"},{"method_slug":"glm","method_name":"GLM"},{"method_slug":"opt","method_name":"OPT"},{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2211.10438","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.10438"}},"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":"deterministic:regex_extraction","url":"https://github.com/IST-DASLab/gptq","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/cornell-zhang/llm-datatypes","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/BlinkDL/RWKV-LM","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/nvidia/tensorrt-llm","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/adlik/smoothquantplus","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mit-han-lab/smoothquant","reach":null}],"summary":{"unverified":5},"by_repo_kind":{"official":{"samples":3,"ran":0,"repositories":1},"listed":{"samples":1,"ran":0,"repositories":1},"found_in_text":{"samples":1,"ran":0,"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":"85fc88c3d658b744","entry":"Quant3Linear","repo":"IST-DASLab/gptq","repo_kind":"found_in_text","path":"quant.py","file_url":"https://github.com/IST-DASLab/gptq/blob/HEAD/quant.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"85fc88c3d658b744"}},{"code_sha256_prefix":"ba983c3543b4f35b","entry":"smooth_lm","repo":"mit-han-lab/smoothquant","repo_kind":"official","path":"smoothquant/smooth.py","file_url":"https://github.com/mit-han-lab/smoothquant/blob/HEAD/smoothquant/smooth.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":"ba983c3543b4f35b"}},{"code_sha256_prefix":"cdb836949df06ba2","entry":"smooth_lm","repo":"adlik/smoothquantplus","repo_kind":"listed","path":"smoothquant/smooth.py","file_url":"https://github.com/adlik/smoothquantplus/blob/HEAD/smoothquant/smooth.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":"cdb836949df06ba2"}},{"code_sha256_prefix":"5cea6036117b53e3","entry":"smooth_ln_fcs","repo":"mit-han-lab/smoothquant","repo_kind":"official","path":"smoothquant/smooth.py","file_url":"https://github.com/mit-han-lab/smoothquant/blob/HEAD/smoothquant/smooth.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":"5cea6036117b53e3"}},{"code_sha256_prefix":"02403dfde3cfaf9f","entry":"smooth_ln_fcs_llama_like","repo":"mit-han-lab/smoothquant","repo_kind":"official","path":"smoothquant/smooth.py","file_url":"https://github.com/mit-han-lab/smoothquant/blob/HEAD/smoothquant/smooth.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":"02403dfde3cfaf9f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}