Re:AMD Alveo V70 AI inference accelerator card
by hyuen on Tuesday January 10, 2023 @12:08PM
(#34327979)
I won't even take a look at the numbers unless they show a PyTorch model running on it, the problem is the big disconnect between HW and SW, realistically, have you ever seen any off-the shelf model running on something other than NVidia?
[ Parent
| on HN ]
Re:AMD Alveo V70 AI inference accelerator card
by kombine on Tuesday January 10, 2023 @12:40PM
(#34328468)
That. I work on the research side and I am still waiting for non-NVIDIA hardware for training deep models.
Re:AMD Alveo V70 AI inference accelerator card
by Narew on Tuesday January 10, 2023 @12:18PM
(#34328156)
It's for inference only not training. In this use case, there is lots of device that's not Nvidia. For server you have Google tpu, for more close to public there is the Apple Neural Engine for example.
Re:AMD Alveo V70 AI inference accelerator card
by frozenport on Tuesday January 10, 2023 @12:53PM
(#34328688)
Google's TPU comes to mind