Skip to content

Add support for CPU Inference#1496

Merged
fxmarty merged 1 commit intohuggingface:mainfrom
vivekkhandelwal1:cpu-inference
Oct 31, 2023
Merged

Add support for CPU Inference#1496
fxmarty merged 1 commit intohuggingface:mainfrom
vivekkhandelwal1:cpu-inference

Conversation

@vivekkhandelwal1
Copy link
Contributor

Refer: AutoGPTQ/AutoGPTQ#385

Signed-Off By: Vivek Khandelwal vivek@nod-labs.com

@vivekkhandelwal1
Copy link
Contributor Author

@fxmarty @SunMarc can you please review this PR?

Copy link
Contributor

@fxmarty fxmarty left a comment

Choose a reason for hiding this comment

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

LGTM

@fxmarty
Copy link
Contributor

fxmarty commented Oct 31, 2023

Can you change the requirements to put AutoGPTQ>=0.5.0?

@vivekkhandelwal1
Copy link
Contributor Author

Can you change the requirements to put AutoGPTQ>=0.5.0?

The transformer's requirements?

@fxmarty
Copy link
Contributor

fxmarty commented Oct 31, 2023

Nevermind. There's actually no auto-gptq in setup.py. You can change AUTOGPTQ_MINIMUM_VERSION in utils/import_utils.py

Refer: AutoGPTQ/AutoGPTQ#385

Signed-Off By: Vivek Khandelwal <vivek@nod-labs.com>
@vivekkhandelwal1
Copy link
Contributor Author

@fxmarty I have updated the PR with the required changes.

Copy link
Contributor

@fxmarty fxmarty left a comment

Choose a reason for hiding this comment

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

LGTM! I will merge it once the corresponding PR in AutoGPTQ is merged :)

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