Minjia Zhang5 papers on this site (2021–2023)DeepSpeed Ulysses: System Optimizations for Enabling Training of Extreme Long Sequence Transformer ModelsSam Ade Jacobs, Masahiro Tanaka, Chengming Zhang, et al.2023Model Tells You What to Discard: Adaptive KV Cache Compression for LLMsSuyu Ge, Yunan Zhang, Liyuan Liu, et al.2023DeepSpeed-MoE: Advancing Mixture-of-Experts Inference and Training to Power Next-Generation AI ScaleSamyam Rajbhandari, Conglong Li, Zhewei Yao, et al.2022ZeroQuant: Efficient and Affordable Post-Training Quantization for Large-Scale TransformersZhewei Yao, Reza Yazdani Aminabadi, Minjia Zhang, et al.2022ZeRO-Offload: Democratizing Billion-Scale Model TrainingJie Ren, Samyam Rajbhandari, Reza Yazdani Aminabadi, et al.2021