-
Notifications
You must be signed in to change notification settings - Fork 719
Add 4 bit inference capability #280
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
base: main
Are you sure you want to change the base?
Conversation
moondream/torch/moondream.py
Outdated
| self._decode_one_tok = torch.compile( | ||
| self._decode_one_tok, fullgraph=True, mode="reduce-overhead" | ||
| ) | ||
| self._vis_enc = torch.compile(self._vis_enc, fullgraph=False, mode="reduce-overhead") |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
@EthanReid what do you think about this? The prefill/decode won't compile for me (even at fp16)
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
It works for me. Since compile is optional, it should be kept.

No description provided.