Skip to content

feature: quantization added#21

Open
dhruv1710 wants to merge 1 commit into
GAIR-NLP:mainfrom
dhruv1710:quantization
Open

feature: quantization added#21
dhruv1710 wants to merge 1 commit into
GAIR-NLP:mainfrom
dhruv1710:quantization

Conversation

@dhruv1710

Copy link
Copy Markdown

Dynamic quantization added to the Linear and LSTM layers, converted to 8bit.

@dhruv1710 dhruv1710 mentioned this pull request Jul 13, 2024
@JoyBoy-Su

Copy link
Copy Markdown
Collaborator

Thanks for your contribution! Maybe we can add a -q option to choose whether or not quantize the model.

@dhruv1710

Copy link
Copy Markdown
Author

That's a good feature, I'll add that

@CoffeeShifter

Copy link
Copy Markdown

You never did

That's a good feature, I'll add that

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