TiledTensor / TiledCUDA

TiledCUDA is a highly efficient kernel template library designed to elevate CUDA C’s level of abstraction for processing tiles.
MIT License
148 stars 10 forks source link

feat(examples): Add a python gemm example. #135

Closed haruhi55 closed 2 months ago

haruhi55 commented 2 months ago
  1. Add a Python GEMM example that uses nvcc to compile GEMM with tiled CUDA primitives.
  2. Enhance the GEMM example to use multiple blocks for processing larger problem sizes.