{"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/zero-shot-dynamic-quantization-for","title":"Zero-Shot Dynamic Quantization for Transformer Inference","arxiv_id":"2211.09744","date":"2022-11-17","proceeding":null,"authors":["Yousef El-Kurdi","Jerry Quinn","Avirup Sil"],"abstract":"We introduce a novel run-time method for significantly reducing the accuracy loss associated with quantizing BERT-like models to 8-bit integers. Existing methods for quantizing models either modify the training procedure,or they require an additional calibration step to adjust parameters that also requires a selected held-out dataset. Our method permits taking advantage of quantization without the need for these adjustments. We present results on several NLP tasks demonstrating the usefulness of this technique.","url_abs":"https://arxiv.org/abs/2211.09744v1","url_pdf":"https://arxiv.org/pdf/2211.09744v1.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":"zero-shot-dynamic-quantization-for","repo_url":"https://github.com/2023-MindSpore-1/ms-code-211/tree/main/DynamicQuant","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"zero-shot-dynamic-quantization-for","repo_url":"https://github.com/2023-MindSpore-4/Code3/tree/main/DynamicQuant","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"zero-shot-dynamic-quantization-for","repo_url":"https://github.com/MindSpore-MS-Code2/code0/tree/main/DynamicQuant","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"zero-shot-dynamic-quantization-for","repo_url":"https://github.com/MindSpore-paper-code-3/code8/tree/main/DynamicQuant","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":"quantization","task_name":"Quantization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2211.09744","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}