Abstract: Sparse Matrix-Matrix Multiplication (SpMM) is a widely used algorithm in Machine Learning, particularly in the increasingly popular Graph Neural Networks (GNNs). SpMM is an essential ...

矩阵乘法是 LLM 的核心计算，快的关键是把大矩阵切成小 tile（比如 128x128），让 GPU 高效算。原来的问题：批次小的时候，tile切得不一样（比如批次 1 时不用大tile，批次 10 时用大tile），乘法顺序变了，结果差了。解决办法：不管批次大小，都用同一种 “tile ...

Abstract: Sparse Matrix Vector multiplication (SpMV) is a fundamental operation in various computational science applications, characterized by a significant degree of inherent parallelism. Recent ...

State Key Laboratory of Tropic Ocean Engineering Materials and Materials Evaluation, School of Marine Science and Engineering, Hainan University, Haikou 570228, China Beijing National Laboratory for ...