You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I installed on Windows 11 and getting the following error. Please help with this issue.
(venv) C:\tut\metavoice-src>python app.py
A matching Triton is not available, some optimizations will not be enabled.
Error caught was: No module named 'triton'
C:\tut\metavoice-src\venv\lib\site-packages\torch\nn\utils\weight_norm.py:30: UserWarning: torch.nn.utils.weight_norm is deprecated in favor of torch.nn.utils.parametrizations.weight_norm.
warnings.warn("torch.nn.utils.weight_norm is deprecated in favor of torch.nn.utils.parametrizations.weight_norm.")
Traceback (most recent call last):
File "C:\tut\metavoice-src\app.py", line 12, in <module>
from fam.llm.fast_inference import TTS
File "C:\tut\metavoice-src\fam\llm\fast_inference.py", line 15, in <module>
from fam.llm.fast_inference_utils import build_model, main
File "C:\tut\metavoice-src\fam\llm\fast_inference_utils.py", line 51, in <module>
torch._inductor.config.fx_graph_cache = (
File "C:\tut\metavoice-src\venv\lib\site-packages\torch\_dynamo\config_utils.py", line 72, in __setattr__
raise AttributeError(f"{self.__name__}.{name} does not exist")
AttributeError: torch._inductor.config.fx_graph_cache does not exist
Hi,
I think, i have temporary solution for this issue.
in the line 48 of the file ("\metavoice/metavoice-src/fam/llm/fast_inference_utils.py ") you have to command the below line.
torch._inductor.config.fx_graph_cache = (
True # Experimental feature to reduce compilation times, will be on by default in future
)
thank you,
Hello,
I installed on Windows 11 and getting the following error. Please help with this issue.
The text was updated successfully, but these errors were encountered: