1

Towards Compute-Aware In-Switch Computing for LLMs Tensor-Parallelism on Multi-GPU Systems
Tensor parallelism (TP) in large-scale LLM inference and training introduces frequent collective operations that dominate inter-GPU …
Chen Zhang, Qijun Zhang, Zhuoshan Zhou, Yijia Diao, Haibo Wang, Zhe Zhou, Zhipeng Tu, Zhiyao Li, Guangyu Sun, Zhuoran Song, Zhigang Ji, Jingwen Leng, Minyi Guo
PDF Cite DOI
HYTE: Flexible Tiling for Sparse Accelerators via Hybrid Static-Dynamic Approaches
Specialized hardware accelerators are widely used for sparse tensor computations. For very large tensors that do not fit in on-chip …
Xintong Li, Zhiyao Li, Mingyu Gao
PDF Cite Code DOI
KAPLA: Scalable NN Accelerator Dataflow Design Space Structuring and Fast Exploring
Dataflow scheduling is of vital importance to neural network (NN) accelerators. Recent scalable NN accelerators support a rich set of …
Zhiyao Li, Mingyu Gao
PDF Cite Code DOI
Adyna: Accelerating Dynamic Neural Networks with Adaptive Scheduling
Dynamic architecture neural networks (DynNNs) are an emerging type of deep learning models that can leverage different processing …
Zhiyao Li, Bohan Yang, Jiaxiang Li, Taijie Chen, Xintong Li, Mingyu Gao
PDF Cite DOI
Spada: Accelerating Sparse Matrix Multiplication with Adaptive Dataflow
Sparse matrix-matrix multiplication (SpGEMM) is widely used in many scientific and deep learning applications. The highly irregular …
Zhiyao Li, Jiaxiang Li, Taijie Chen, Dimin Niu, Hongzhong Zheng, Yuan Xie, Mingyu Gao
PDF Cite Code Video DOI