Skip to content
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

fix cmake version, padding for a8w4dq, lint... #680

Merged
merged 4 commits into from
May 5, 2024
Merged

fix cmake version, padding for a8w4dq, lint... #680

merged 4 commits into from
May 5, 2024

Conversation

mikekgfb
Copy link
Contributor

@mikekgfb mikekgfb commented May 5, 2024

fix cmake version, padding for a8w4dq, lint...

@facebook-github-bot facebook-github-bot added the CLA Signed This label is managed by the Meta Open Source bot. label May 5, 2024
Michael Gschwind added 2 commits May 4, 2024 21:26
@malfet
Copy link
Contributor

malfet commented May 6, 2024

For the PR that adds 257 lines of code, it would be nice to have a bit more description.

Comment on lines +87 to +109
#
#
# class Int8DynActInt4WeightQuantizer(QuantHandler):
# def __init__(self, model: nn.Module, device="cpu", tokenizer=None, **kwargs):
# import torchao.quantization.quant_api as quant_api
#
# self.model_ = model
# self.device = device
# self.tokenizer = tokenizer
# self.quantizer = quant_api.Int8DynActInt4WeightQuantizer(
# **kwargs, precision=get_precision(), scales_precision=get_precision()
# )
#
# def create_quantized_state_dict(self) -> Dict: # "StateDict"
# pass
#
# def convert_for_runtime(self) -> nn.Module:
# pass
#
# def quantized_model(self) -> nn.Module:
# return self.quantizer.quantize(self.model_)
#
#
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Why are we leaving commented out code here?

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Yes, I was planning to do a follow-up PR to remove this

@@ -22,7 +22,7 @@ blobfile

# Build tools
wheel
cmake
cmake>=3.24
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

What does it achieves?

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Resolve #679

malfet pushed a commit that referenced this pull request Jul 17, 2024
* fix cmake version, p[adding for a8w4dq, lint...

* fix cmake version, p[adding for a8w4dq, lint...

* updates

* fix
malfet pushed a commit that referenced this pull request Jul 17, 2024
* fix cmake version, p[adding for a8w4dq, lint...

* fix cmake version, p[adding for a8w4dq, lint...

* updates

* fix
malfet pushed a commit that referenced this pull request Jul 17, 2024
* fix cmake version, p[adding for a8w4dq, lint...

* fix cmake version, p[adding for a8w4dq, lint...

* updates

* fix
malfet pushed a commit that referenced this pull request Jul 17, 2024
* fix cmake version, p[adding for a8w4dq, lint...

* fix cmake version, p[adding for a8w4dq, lint...

* updates

* fix
malfet pushed a commit that referenced this pull request Jul 17, 2024
* fix cmake version, p[adding for a8w4dq, lint...

* fix cmake version, p[adding for a8w4dq, lint...

* updates

* fix
malfet pushed a commit that referenced this pull request Jul 17, 2024
* fix cmake version, p[adding for a8w4dq, lint...

* fix cmake version, p[adding for a8w4dq, lint...

* updates

* fix
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
CLA Signed This label is managed by the Meta Open Source bot.
Projects
None yet
Development

Successfully merging this pull request may close these issues.

4 participants