Skip to content

Conversation

@yuchiwang
Copy link
Contributor

issue 1376 . Add a counter and print in the quant logs how many actual add_batch or inputs are captured by the quantization process for each module.

@Qubitium Qubitium self-requested a review March 9, 2025 04:48
@Qubitium
Copy link
Collaborator

Qubitium commented Mar 9, 2025

@yuchiwang Thanks for the PR. This will be very useful for MoE modules.

@Qubitium Qubitium merged commit ad9fce2 into ModelCloud:main Mar 9, 2025
1 check passed
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.

2 participants