Toward QoS-Awareness and Improved Utilization of Spatial Multitasking GPUs von Zhang, Wei, Chen, Quan, Zheng, Ningxin, Cui, Weihao, Fu, Kaihua, Guo, Minyi

Volltext

Online Streaming Video Super-Resolution with Convolutional Look-Up Table von Yin, Guanghao, Qu, Zefan, Jiang, Xinyang, Jiang, Shan, Han, Zhenhua, Zheng, Ningxin, Yang, Huan, Liu, Xiaohong, Yang, Yuqing, Li, Dongsheng, Qiu, Lili

Volltext

Online Video Super-Resolution with Convolutional Kernel Bypass Grafts von Xiao, Jun, Jiang, Xinyang, Zheng, Ningxin, Yang, Huan, Yang, Yifan, Yang, Yuqing, Li, Dongsheng, Lam, Kin-Man

Volltext

Capstone English Language Learners Portfolio von Zheng, Ningxin

Volltext bestellen

nn-METER: Towards Accurate Latency Prediction of DNN Inference on Diverse Edge Devices von Zhang, Li Lyna, Han, Shihao, Wei, Jianyu, Zheng, Ningxin, Cao, Ting, Liu, Yunxin

Volltext

ShadowKV: KV Cache in Shadows for High-Throughput Long-Context LLM Inference von Sun, Hanshi, Chang, Li-Wen, Bao, Wenlei, Zheng, Size, Zheng, Ningxin, Liu, Xin, Dong, Harry, Chi, Yuejie, Chen, Beidi

Volltext bestellen

EfficientViT: Memory Efficient Vision Transformer with Cascaded Group Attention von Liu, Xinyu, Peng, Houwen, Zheng, Ningxin, Yang, Yuqing, Hu, Han, Yuan, Yixuan

Volltext bestellen

FLUX: Fast Software-based Communication Overlap On GPUs Through Kernel Fusion von Chang, Li-Wen, Bao, Wenlei, Hou, Qi, Jiang, Chengquan, Zheng, Ningxin, Zhong, Yinmin, Zhang, Xuanrun, Song, Zuquan, Yao, Chengji, Jiang, Ziheng, Lin, Haibin, Jin, Xin, Liu, Xin

Volltext bestellen

SpaceEvo: Hardware-Friendly Search Space Design for Efficient INT8 Inference von Zhang, Li Lyna, Wang, Xudong, Xu, Jiahang, Zhang, Quanlu, Wang, Yujing, Yang, Yuqing, Zheng, Ningxin, Cao, Ting, Yang, Mao

Volltext bestellen

Online Video Super-Resolution with Convolutional Kernel Bypass Graft von Xiao, Jun, Jiang, Xinyang, Zheng, Ningxin, Yang, Huan, Yang, Yifan, Yang, Yuqing, Li, Dongsheng, Lam, Kin-Man

Volltext bestellen

Online Streaming Video Super-Resolution with Convolutional Look-Up Table von Yin, Guanghao, Qu, Zefan, Jiang, Xinyang, Jiang, Shan, Han, Zhenhua, Zheng, Ningxin, Liu, Xiaohong, Yang, Huan, Yang, Yuqing, Li, Dongsheng, Qiu, Lili

Volltext bestellen

PIT: Optimization of Dynamic Sparse Deep Learning Models via Permutation Invariant Transformation von Zheng, Ningxin, Jiang, Huiqiang, Zhang, Quanlu, Han, Zhenhua, Yang, Yuqing, Ma, Lingxiao, Yang, Fan, Zhang, Chengruidong, Qiu, Lili, Yang, Mao, Zhou, Lidong

Volltext bestellen

Full-Cycle Energy Consumption Benchmark for Low-Carbon Computer Vision von Li, Bo, Jiang, Xinyang, Bai, Donglin, Zhang, Yuge, Zheng, Ningxin, Dong, Xuanyi, Liu, Lu, Yang, Yuqing, Li, Dongsheng

Volltext bestellen

URSA: Precise Capacity Planning and Contention-aware Scheduling for Public Clouds von Zheng, Ningxin, Chen, Quan, Yang, Yong, Zhang, Wei, Li, Jin, Zheng, Wenli, Guo, Minyi

Volltext bestellen

ShadowKV: KV Cache in Shadows for High-Throughput Long-Context LLM Inference von Sun, Hanshi, Li-Wen, Chang, Bao, Wenlei, Size Zheng, Zheng, Ningxin, Liu, Xin, Dong, Harry, Chi, Yuejie, Chen, Beidi

Volltext

Towards QoS-Aware and Resource-Efficient GPU Microservices Based on Spatial Multitasking GPUs In Datacenters von Zhang, Wei, Chen, Quan, Fu, Kaihua, Zheng, Ningxin, Huang, Zhiyi, Leng, Jingwen, Li, Chao, Zheng, Wenli, Guo, Minyi

Volltext bestellen

EfficientViT: Memory Efficient Vision Transformer with Cascaded Group Attention von Liu, Xinyu, Houwen Peng, Zheng, Ningxin, Yang, Yuqing, Hu, Han, Yuan, Yixuan

Volltext

Method and device for training classifier and predicting application performance expansibility von ZHENG NINGXIN, YANG YONG

Volltext bestellen

PERFORMING DYNAMIC SPARSE COMPUTATION ON DENSE COMPUTATION-EFFICIENT COMPUTING DEVICES von YANG, Mao, ZHENG, Ningxin, JIANG, Huiqiang, ZHOU, Lidong, QIU, Lili, MA, Lingxiao, HAN, Zhenhua, ZHANG, Quanlu, YANG, Fan, YANG, Yuqing

Volltext bestellen

SPARSITY FOR NEURAL NETWORK MODELS BASED ON SPARSITY ATTRIBUTES von YANG, Mao, ZHENG, Ningxin, ZHOU, Lidong, WANG, Yang, MA, Lingxiao, ZHANG, Quanlu, YANG, Fan, YANG, Yuqing

Volltext bestellen