Skip to content

Handle GPTQ-Marlin loading in GPTQMarlinWeightLoader #2300

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

Merged
merged 1 commit into from
Jul 31, 2024

Conversation

danieldk
Copy link
Member

@danieldk danieldk commented Jul 24, 2024

What does this PR do?

The GPTWeightLoader was structured like this in pseudocode:

if marlin:
  Set up tensors in a way that GPTQ-Marlin expects
else:
  Set up tensors in a way that ExLlama/GPTQ/AWQ expect

However, the GPT-Marlin implementation details should really be in the marlin module. So move the former part out to a separate GPTQMarlinWeightsLoader.

Before submitting

  • This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case).
  • Did you read the contributor guideline,
    Pull Request section?
  • Was this discussed/approved via a Github issue or the forum? Please add a link
    to it if that's the case.
  • Did you make sure to update the documentation with your changes? Here are the
    documentation guidelines, and
    here are tips on formatting docstrings.
  • Did you write any new necessary tests?

Who can review?

Anyone in the community is free to review the PR once the tests have passed. Feel free to tag
members/contributors who may be interested in your PR.

@drbh drbh self-assigned this Jul 25, 2024
drbh
drbh previously approved these changes Jul 29, 2024
Copy link
Collaborator

@drbh drbh left a comment

Choose a reason for hiding this comment

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

lgtm

The `GPTWeightLoader` was structured like this in pseudocode:

if marlin:
  Set up tensors in a way that GPTQ-Marlin expects
else:
  Set up tensors in a way that ExLlama/GPTQ/AWQ expect

However, the GPT-Marlin implementation details should really be in the
`marlin` module. So move the former part out to a separate
`GPTQMarlinWeightsLoader`.
@danieldk danieldk force-pushed the maintenance/gptq-marlin-loader branch from 5b6ba33 to f5f09ae Compare July 31, 2024 06:58
@danieldk danieldk merged commit 34f7dcf into main Jul 31, 2024
9 checks passed
@danieldk danieldk deleted the maintenance/gptq-marlin-loader branch July 31, 2024 11:08
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