Hello, Jason J.G. White, le mer. 12 nov. 2025 19:08:36 -0500, a ecrit: > I don't know whether this is improved if you have appropriate GPU processing > for the neural network models.
Yes, GPUs would improve latency a lot. Submitting a task to a GPU does have some latency, but that's measured as a few microseconds only, so the parallelism benefit of GPUs can be very ample. > Piper was unusably slow on my machine, but I > didn't investigate deeply enough to find out whether it was using the GPU. Most probably it wasn't, it's hard to get things correctly set up for GPU computing to work :) Samuel
