Improving Speed with CUDA

locuslab / mpc.pytorch

A fast and differentiable model predictive control (MPC) solver for PyTorch.

https://locuslab.github.io/mpc.pytorch/

MIT License

872 stars 146 forks source link

Open wert93 opened 3 years ago

wert93 commented 3 years ago

Is there a way to improve the speed performance of the solver by doing the computation on GPU? If so, which tensors should be assigned to 'cuda'?

Roythuly commented 2 years ago

I find if you use your CPU with this repo, the speed performance would be improved well