KDFlow: A User-Friendly and Efficient Knowledge Distillation Framework for Large Language Models
KDFlow:一种用户友好且高效的大型语言模型知识蒸馏框架
机构 * Key Laboratory of Big Data & Artificial Intelligence in Transportation, (Beijing Jiaotong University), Ministry of Education(大数据与人工智能交通运输联合实验室,(北京交通大学)教育部) ; School of Computer Science and Technology, Beijing Jiaotong University, Beijing, China(计算机科学与技术学院,北京交通大学,北京,中国) ; Tencent Inc, China(腾讯公司,中国)
专题命中 效率与部署 :large language model(title,abstract);language model(title,abstract);LLM(abstract,abstract_cn);分类 cs.CL、cs.AI、cs.LG
AI总结 KDFlow通过解耦架构和SGLang实现高效蒸馏,平衡通信成本与性能,实现1.44至6.36倍加速。
Comments 9 pages, 4 figures, 4 tables, code is available at: https://github.com/songmzhang/KDFlow