Google Announces A3 Supercomputers with Nvidia H100 GPUs (cloud.google.com) 4 points by osti 3y ago ↗ HN
[–] ftxbro 3y ago ↗ When they were using A100 I knew that H100 would be the next ones. But what are the next ones now?
[–] sandGorgon 3y ago ↗ can someone explain why this is nvidia and not TPU ?I thought that TPU were much better than GPU at ML workloads. And cheaper overall for Google too. Why is this nvidia instead of TPU ? [–] osti 3y ago ↗ I'd assume there is integration work involved to train on TPU, so some companies would want to stay on NVIDIA.AWS also offers their own training chip instances (Trainium) while also providing NVIDIA instance types (P).
[–] osti 3y ago ↗ I'd assume there is integration work involved to train on TPU, so some companies would want to stay on NVIDIA.AWS also offers their own training chip instances (Trainium) while also providing NVIDIA instance types (P).
3 comments
[ 2.4 ms ] story [ 15.1 ms ] threadI thought that TPU were much better than GPU at ML workloads. And cheaper overall for Google too. Why is this nvidia instead of TPU ?
AWS also offers their own training chip instances (Trainium) while also providing NVIDIA instance types (P).