Who uses Google TPUs for inference in production? arthurdelerue on March 11, 2024 at 11:22 Hacker News: Front Page

I am really puzzled by TPUs. I’ve been reading everywhere that TPUs are powerful and a great alternative to NVIDIA.

I have been playing with TPUs for a couple of months now, and to be honest I don’t understand how can people use them in production for inference:

– almost no resources online showing how to run modern generative models like Mistral, Yi 34B, etc. on TPUs
– poor compatibility between JAX and Pytorch
– very hard to understand the memory consumption of the TPU chips (no nvidia-smi equivalent)
– rotating IP addresses on TPU VMs
– almost impossible to get my hands on a TPU v5

Is it only me? Or did I miss something?

I totally understand that TPUs can be useful for training though.

Comments URL: https://news.ycombinator.com/item?id=39670121

Points: 26

# Comments: 6

Leave a Reply

Your email address will not be published. Required fields are marked *