Open yukiarimo opened 1 month ago
Same issue for Apple M1 Max
But as I understood the project will not be supported yet, so we need to figure out together how to fix it
What I have found:
PYTORCH_ENABLE_MPS_FALLBACK=1
There's a topic under https://github.com/pytorch/pytorch/issues/77764 to implement missing functionality
What I have did locally as workaround:
open .venv/lib/python3.10/site-packages/transformers/generation/utils.py
and comment the part for mps
Same issue from Pro M1 too
I am running "distilgpt2". and "t5-small" models for simple prompts
I guess you would need more computational power and storage to manage the model check-points
Same issue from Mac book air M1
I am running "tts_models/multilingual/multi-dataset/xtts_v2".
Describe the bug
To Reproduce
Run this:
Expected behavior
No response
Logs
No response
Environment
Additional context
Hardware: MacBook Pro M1