News for hackers. Stuff that matters.
Re:AMD Alveo V70 AI inference accelerator card by marcyb5st on Tuesday January 10, 2023 @03:13PM (#34330817)
Because of VRAM. Even a simple model for language can easily max out a 4090.

Also, ROC-M is a bit of a mess to setup. With Nvidia i just need to install cuda, cudnn and then pip install tensorflow/pytorch.

There are no comments on this comment yet.