praeclarum / webgpu-torch

Tensor computation with WebGPU acceleration
MIT License
583 stars 17 forks source link

Matmul #9

Closed praeclarum closed 1 year ago

praeclarum commented 1 year ago

Implements the four cases:

  1. dot Vector and Vector
  2. mv Vector and Matrix using m^T*v
  3. mv Matrix and Vector
  4. bmm Batched Matrix and Matrix with broadcasting