| Break the Sequential Dependency of LLM Inference Using Lookahead Decoding Y Fu, P Bailis, I Stoica, H Zhang arXiv preprint arXiv:2402.02057, 2024 | 99* | 2024 |
| Efficient LLM Scheduling by Learning to Rank Y Fu, S Zhu, R Su, A Qiao, I Stoica, H Zhang arXiv preprint arXiv:2408.15792, 2024 | 7* | 2024 |
| ShiftAddLLM: Accelerating Pretrained LLMs via Post-Training Multiplication-Less Reparameterization H You, Y Guo, Y Fu, W Zhou, H Shi, X Zhang, S Kundu, A Yazdanbakhsh, ... arXiv preprint arXiv:2406.05981, 2024 | 5 | 2024 |
| When linear attention meets autoregressive decoding: Towards more effective and efficient linearized large language models H You, Y Fu, Z Wang, A Yazdanbakhsh, YC Lin arXiv preprint arXiv:2406.07368, 2024 | 3 | 2024 |
| Neuron Sensitivity-Guided Test Case Selection D Huang, Q Bu, Y Fu, Y Qing, X Xie, J Chen, H Cui ACM Transactions on Software Engineering and Methodology 33 (7), 1-32, 2024 | 2* | 2024 |
| Efficiently Serving LLM Reasoning Programs with Certaindex Y Fu, J Chen, S Zhu, Z Fu, Z Dai, A Qiao, H Zhang arXiv preprint arXiv:2412.20993, 2024 | | 2024 |
| AMPipe: Accelerating MoE Model Training with Intra-Block Pipelining Y Fu, Q Yuhao, S Zhao, F Li, B Xiao, D HUANG, H Cui | | |
Hao ZhangUC San DiegoVerified email at ucsd.edu
