Speeding up inference tips/tricks? [thread]

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

20.59k stars 2.09k forks source link

Speeding up inference tips/tricks? [thread] #224

Open mepc36 opened 1 year ago

mepc36 commented 1 year ago

Anyone have any tips/tricks on how to speed up MusicGen inference? I'm already using the smallest model possible, any help is appreciated (multi-GPU inference, etc.) Thanks!

zeke-john commented 6 months ago

Any update, i'm also trying to use multi-GPU inference to speed up MusicGen inference for the medium. Any luck?