CUDA, GPUs, and

Is there a tutorial / sample repo somewhere that solves this problem:

  1. you have a machine with some nvidia GPUs
  2. you have CUDA installed
  3. you follow this tutorial / install this package
  4. now you can use / OWL with GPGPU support ?

The closest to this seems to be; write code in OWL, export a ONNX, run some python/julia script to read/optimize ONNX, load weights back into OWL. This seems to limit us to situations where the compute graph is static …


1 Like