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

[GPTQ Modifier UX] Add default scheme #61

Merged
merged 2 commits into from
May 22, 2024
Merged

[GPTQ Modifier UX] Add default scheme #61

merged 2 commits into from
May 22, 2024

Conversation

rahul-tuli
Copy link
Member

This PR adds a class method in QuantizationScheme, to load a default scheme; this is needed for PR neuralmagic/sparseml#2263

weights = QuantizationArgs(num_bits=8, symmetric=True)

# default to 8 bit integer asymmetric quantization
input_activations = QuantizationArgs(num_bits=8, symmetric=False)
Copy link

Choose a reason for hiding this comment

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

vLLM only supports symmetric quantization so lets default this to True as well

@bfineran bfineran merged commit b76acf4 into main May 22, 2024
1 check passed
@bfineran bfineran deleted the add-default-scheme branch May 22, 2024 15:35
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants