-
Notifications
You must be signed in to change notification settings - Fork 443
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
deepspeed for XTTS #569
Comments
Thanks @hslr4 , those are interesting findings! I will try rebuilding PyTorch here with |
OK, pytorch passed with You should not need to recompile torchvision or torchaudio wheels I don't believe. |
Thank you for the quick reply and help @dusty-nv ! When I wanted to do some testing regarding inference speed, I noticed that tensorrt is currently only used in After I added it to
Seems like using deepspeed on xtts's gpt is more helpful than tensorrt on the hifigan_decoder. Actually the speedup by trt appears comparably low, so I'm still not sure if I'm actually using it right 🙈 Did you test how effective the hifigan_decoder_trt is before? |
Since the coqui docs recommend the use of
deepspeed
to speed up their XTTS model I wanted to give this a try.To make it work I did the following:
USE_NCCL=1
because deepspeed requires nccl.libaio-dev
since a warning during the installation of deepspeed recommends it (though I am not sure if it is actually required).setuptools
to 69.5.1.TORCH_CUDA_ARCH_LIST="7.2;8.7" pip3 install deepspeed
.Indeed inference of XTTS is about twice as fast as without deepspeed (still slower than other TTS models, that do not support voice cloning or multilinguality).
Would it make sense to provide pre-built pytorch versions with nccl for such use-cases?
The text was updated successfully, but these errors were encountered: