I'm talking about holistic efforts like OpenCL, and standards that would be equivalent to Nvidia's "Compute Capability" versioning.
The basic underlying tech can be agreed on, but Apple/AMD/Intel all have different GPU priorities that limit their ability to agree on a CUDA-adjacent hardware platform.
The basic underlying tech can be agreed on, but Apple/AMD/Intel all have different GPU priorities that limit their ability to agree on a CUDA-adjacent hardware platform.