[Nevin1901]

How fast are coldstarts, and how do you compare against other gpu providers (runpod modal etc)

[xena]

The slowest part is loading weights into vram in my experience. I haven't done benchmarking on that. What kind of benchmark would you like to see?

[ipsum2]

I would like to see time to first inference for typical models (llama-7b first token, SDXL 1 step, etc)