Donglin Zhuang

15 papers A* 2A 2B 1Journal 8Unranked 2

Year	Rank	Type	Title / Venue / Authors
2025	J	`jnl`	Kitty: Accurate and Efficient 2-bit KV Cache Quantization with Dynamic Channel-wise Precision Boost. CoRR Haojun Xia, Xiaoxia Wu, Jisen Li, Robert Wu, Junxiong Wang, Jue Wang, Chenxi Li, Aman Singhal, Alay Dilipbhai Shah, Alpay Ariyak, Donglin Zhuang, Zhongzhu Zhou, Ben Athiwaratkun, Zhen Zheng, Shuaiwen Leon Song
2024	J	`jnl`	FP6-LLM: Efficiently Serving Large Language Models Through FP6-Centric Algorithm-System Co-Design. CoRR Haojun Xia, Zhen Zheng, Xiaoxia Wu, Shiyang Chen, Zhewei Yao, Stephen Youn, Arash Bakhtiari, Michael Wyatt, Donglin Zhuang, Zhongzhu Zhou, Olatunji Ruwase, Yuxiong He, Shuaiwen Leon Song
2024	A*	`conf`	MonoNN: Enabling a New Monolithic Optimization Space for Neural Network Inference Tasks on Modern GPU-Centric Architectures. OSDI Donglin Zhuang, Zhen Zheng, Haojun Xia, Xiafei Qiu, Junjie Bai, Wei Lin, Shuaiwen Leon Song
2024	—	`conf`	Quant-LLM: Accelerating the Serving of Large Language Models via FP6-Centric Algorithm-System Co-Design on Modern GPUs. USENIX ATC Haojun Xia, Zhen Zheng, Xiaoxia Wu, Shiyang Chen, Zhewei Yao, Stephen Youn, Arash Bakhtiari, Michael Wyatt, Donglin Zhuang, Zhongzhu Zhou, Olatunji Ruwase, Yuxiong He, Shuaiwen Leon Song
2023	J	`jnl`	Flash-LLM: Enabling Cost-Effective and Highly-Efficient Large Generative Model Inference with Unstructured Sparsity. CoRR Haojun Xia, Zhen Zheng, Yuchao Li, Donglin Zhuang, Zhongzhu Zhou, Xiafei Qiu, Yong Li, Wei Lin, Shuaiwen Leon Song
2023	J	`jnl`	Flash-LLM: Enabling Low-Cost and Highly-Efficient Large Generative Model Inference With Unstructured Sparsity. Proc. VLDB Endow. Haojun Xia, Zhen Zheng, Yuchao Li, Donglin Zhuang, Zhongzhu Zhou, Xiafei Qiu, Yong Li, Wei Lin, Shuaiwen Leon Song
2022	A	`conf`	Bring orders into uncertainty: enabling efficient uncertain graph processing via novel path sampling on multi-accelerator systems. ICS Heng Zhang, Lingda Li, Hang Liu, Donglin Zhuang, Rui Liu, Chengying Huan, Shuang Song, Dingwen Tao, Yongchao Liu, Charles He, Yanjun Wu, Shuaiwen Leon Song
2022	J	`jnl`	DynamAP: Architectural Support for Dynamic Graph Traversal on the Automata Processor. ACM Trans. Archit. Code Optim. Yiding Liu, Xingyao Zhang, Donglin Zhuang, Xin Fu, Shuaiwen Song
2022	—	`conf`	Randomness in Neural Network Training: Characterizing the Impact of Tooling. MLSys Donglin Zhuang, Xingyao Zhang, Shuaiwen Song, Sara Hooker
2021	B	`conf`	An efficient uncertain graph processing framework for heterogeneous architectures. PPoPP Heng Zhang, Lingda Li, Donglin Zhuang, Rui Liu, Shuang Song, Dingwen Tao, Yanjun Wu, Shuaiwen Leon Song
2021	A	`conf`	ClickTrain: efficient and accurate end-to-end deep learning training via fine-grained architecture-preserving pruning. ICS Chengming Zhang, Geng Yuan, Wei Niu, Jiannan Tian, Sian Jin, Donglin Zhuang, Zhe Jiang, Yanzhi Wang, Bin Ren, Shuaiwen Leon Song, Dingwen Tao
2021	J	`jnl`	Enabling Highly Efficient Capsule Networks Processing Through Software-Hardware Co-Design. IEEE Trans. Computers Xingyao Zhang, Xin Fu, Donglin Zhuang, Chenhao Xie, Shuaiwen Leon Song
2021	J	`jnl`	Randomness In Neural Network Training: Characterizing The Impact of Tooling. CoRR Donglin Zhuang, Xingyao Zhang, Shuaiwen Leon Song, Sara Hooker
2021	A*	`conf`	η-LSTM: Co-Designing Highly-Efficient Large LSTM Training via Exploiting Memory-Saving and Architectural Design Opportunities. ISCA Xingyao Zhang, Haojun Xia, Donglin Zhuang, Hao Sun, Xin Fu, Michael B. Taylor, Shuaiwen Leon Song
2020	J	`jnl`	An Efficient End-to-End Deep Learning Training Framework via Fine-Grained Pattern-Based Pruning. CoRR Chengming Zhang, Geng Yuan, Wei Niu, Jiannan Tian, Sian Jin, Donglin Zhuang, Zhe Jiang, Yanzhi Wang, Bin Ren, Shuaiwen Leon Song, Dingwen Tao