facebookresearch / audiocraft

Audiocraft is a library for audio processing and generation with deep learning. It features the state-of-the-art EnCodec audio compressor / tokenizer, along with MusicGen, a simple and controllable music generation LM with textual and melodic conditioning.
MIT License
20.91k stars 2.14k forks source link

Is it possible to use multiple GPU for single generate? #150

Open roseodimm opened 1 year ago

roseodimm commented 1 year ago

Is it possible to use combine Vram from multiple GPU like in Text to generate webui "oobabooga" that will use total Vram of multiple gpu when load the model or generate the reply?

I have x4 of 8gb GPU and I can't use melody mode becasue it need more Vram.