关注
Mengdi Wu
Mengdi Wu
Carnegie Mellon University
在 andrew.cmu.edu 的电子邮件经过验证
标题
引用次数
引用次数
年份
Finding the task-optimal low-bit sub-distribution in deep neural networks
R Dong, Z Tan, M Wu, L Zhang, K Ma
International Conference on Machine Learning, 5343-5359, 2022
132022
Graphpipe: Improving performance and scalability of dnn training with graph pipeline parallelism
B Jeon, M Wu, S Cao, S Kim, S Park, N Aggarwal, C Unger, D Arfeen, ...
arXiv preprint arXiv:2406.17145, 2024
32024
FlexLLM: A System for Co-Serving Large Language Model Inference and Parameter-Efficient Finetuning
X Miao, G Oliaro, X Cheng, M Wu, C Unger, Z Jia
arXiv preprint arXiv:2402.18789, 2024
32024
A Multi-Level Superoptimizer for Tensor Programs
M Wu, X Cheng, O Padon, Z Jia
arXiv preprint arXiv:2405.05751, 2024
2024
系统目前无法执行此操作，请稍后再试。
文章 1–4