Hacker News new | ask | show | jobs
by tekawade 332 days ago
I want #3 be able to connect NVIDIA GPU with Apple Silicon and run CUDA. Take advantage of apple silicon + unified memory + GPU + CUDA with PyTorch, JAX or TensorFlow.

Haven’t really explored MLX so can’t speak about it.
1 comments
musicale 331 days ago
Nvidia already has unified memory on Grace Blackwell etc.

I guess M5 Blackwell could be better, but there are business and technical barriers to making that happen.

link
tekawade 329 days ago
I meant Apple ecosystem does not support NVIDIA GPUs anymore. NVIDIA itself with CUDA Support DMA.
link