• Lei Wang's avatar
    [Bugfix] Fix Hopper GEMM layout for small tile size (#497) · c93e8695
    Lei Wang authored
    * [Enhancement] Improve GEMM layout function and documentation
    
    * Added detailed documentation for the makeGemmABLayout function, explaining parameters and layout selection strategies.
    * Updated the layout selection logic to use mat_continuous consistently, enhancing clarity and correctness in memory layout calculations.
    * Adjusted the InferLayout method to reflect changes in the layout function, ensuring accurate matrix dimension handling for transposed cases.
    
    * lint fix
    c93e8695
gemm_layouts.cc 22.5 KB