Zheng, Size

1. DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model
   2024/05/07 by DeepSeek-AI, Aixin Liu, Bei Feng +310 · 5 voices · 237 citations
   Computer Science · #Expert finding and Q&A systems #Topic Modeling #Speech and dialogue systems
2. Atom: Low-bit Quantization for Efficient and Accurate LLM Serving
   2023/10/29 by Yilong Zhao, Chien‐Yu Lin, Zhao, Yilong +17 · 40 citations
   Computer Science · #FOS: Computer and information sciences #Machine Learning (cs.LG) #Multimodal Machine Learning Applications #Natural Language Processing Techniques #Topic Modeling
3. ShadowKV: KV Cache in Shadows for High-Throughput Long-Context LLM Inference
   2024/10/28 by Li‐Wen Chang, Sun, Hanshi, Chang, Li-Wen +14 · 27 citations
   Computer Science · #Anomaly Detection Techniques and Applications #Computation and Language (cs.CL) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Network Packet Processing and Optimization #Time Series Analysis and Forecasting
4. Comet: Fine-grained Computation-communication Overlapping for Mixture-of-Experts
   2025/02/27 by S. J. Zhang, Ningxin Zheng, Zhang, Shulai +20 · 11 citations
   Computer Science · #Advanced Neural Network Applications #Mobile Crowdsensing and Crowdsourcing #Big Data and Digital Economy
5. Triton-distributed: Programming Overlapping Kernels on Distributed AI Systems with the Triton Compiler
   2025/04/28 by Size Zheng, Zheng, Size, Wenlei Bao +40 · 9 citations
   Computer Science · #Parallel Computing and Optimization Techniques #Advanced Neural Network Applications #Distributed and Parallel Computing Systems
6. TileLink: Generating Efficient Compute-Communication Overlapping Kernels using Tile-Centric Primitives
   2025/03/26 by Zheng, Size, Fang, Jin, Zheng, Xuegui +9 · 7 citations
   #Distributed #FOS: Computer and information sciences #Parallel #and Cluster Computing (cs.DC)
7. HASCO: Towards Agile HArdware and Software CO-design for Tensor Computation
   2021/05/04 by Xiao, Qingcheng, Zheng, Size, Wu, Bingzhe +3 · 2 citations
   #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Hardware Architecture (cs.AR)
8. MxMoE: Mixed-precision Quantization for MoE with Accuracy and Performance Co-Design
   2025/05/09 by Haojie Duanmu, Duanmu, Haojie, Xiuhong Li +11 · 9 citations
   Computer Science · #Advanced Neural Network Applications #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Mobile Crowdsensing and Crowdsourcing #Stochastic Gradient Optimization Techniques
9. MegaScale-MoE: Large-Scale Communication-Efficient Training of Mixture-of-Experts Models in Production
   2025/05/16 by Jin, Chao, Jiang, Ziheng, Bai, Zhihao +16 · 6 citations
   #Distributed #FOS: Computer and information sciences #Machine Learning (cs.LG) #Parallel #and Cluster Computing (cs.DC)