Conversation
…ialization-bug Ensure server uses spawn start method for CUDA workers
…-in-uma.py Adjust UMA offline mode handling
|
|
cplett
left a comment
cplett
left a comment
There was a problem hiding this comment.
Hey,
Thank you very much for fixing this! Looks good to me.
There’s just one minor point regarding the warning that needs a bit of clarification. Once that’s addressed, I’ll merge the PR.
| if self.check_for_model_files(basemodel=basemodel, cache_dir=cache_dir): | ||
| print( | ||
| "WARNING: No model files were detected. This might lead to subsequent errors." | ||
| ) |
There was a problem hiding this comment.
Would there be any downside to keeping this warning? If not, I think it would make sense to leave it in place with the corrected logic:
if not self.check_for_model_files(basemodel=basemodel, cache_dir=cache_dir):
print(
"WARNING: No model files were detected. This might lead to subsequent errors."
)
There was a problem hiding this comment.
not really but seems counter intuitive that the check is done no matter what =)
assuming this check is basically free it should be fine either way
There was a problem hiding this comment.
I've changed the model file detection a little. I hope this is fine by you.
Signed-off-by: Christoph Plett <plett@faccts.de>
|
@kevinkong98 Thanks again for the contribution! |
3 participants
Fixes #28 and change to the UMA model offline mode (the previous cache detection when using offline mode have the logic flipped)