tiny-cuda-nn icon indicating copy to clipboard operation
tiny-cuda-nn copied to clipboard

What is the purpose of this software ?

Open lix19937 opened this issue 1 year ago • 3 comments

What is the purpose of this software and what are its application examples ?

Between pytorch and tensorrt ? For training or inference ?

Or to make wheels. ?

lix19937 avatar May 24 '24 05:05 lix19937

As far as I can tell, the intended use is to just locally build and install this using setup.py in bindings/torch. Then you can use it as part of pytorch networks in Python. You need to have the CUDA toolkit available for building .cu files and to have the libtorch library (c++ version of torch) for the matching version of CUDA.

The C++ side of things is a bit more sparse. I basically had to duplicate the functionality of modules.py and bindings.cpp using libtorch. It would be much more convenient if the Module class in bindings/torch/bindings.cpp were a) exposed in a header file, and b) was itself a torch::nn::Module so that there wouldn't need to be the python middle layer.

cogwheel avatar May 31 '24 16:05 cogwheel

The C++ side of things is a bit more sparse. I basically had to duplicate the functionality of modules.py and bindings.cpp using libtorch. It would be much more convenient if the Module class in bindings/torch/bindings.cpp were a) exposed in a header file, and b) was itself a torch::nn::Module so that there wouldn't need to be the python middle layer.

We released this publicly earlier this week if you want to have a look: https://github.com/fbriggs/lifecast_public/commit/aaa1000ccfcd9bf94a143fc21300fe6607636342#diff-aef1b984940ceb407dca09e98a080c07a1cecbb1ae6b386caa0028e03e45bc48

cogwheel avatar Jun 07 '24 15:06 cogwheel

Thanks both.

lix19937 avatar Jun 12 '24 01:06 lix19937