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

Use GPTQ-Marlin for supported GPTQ configurations #2111

Merged
merged 1 commit into from
Jul 1, 2024

Conversation

danieldk
Copy link
Member

@danieldk danieldk commented Jun 24, 2024

What does this PR do?

GPTQ-Marlin is currently the best-performing kernel for GPTQ models. So let's use it by default if the kernels are installed, the GPU supports it, and the kernels support the configuration.

For models generated by text-generation-server quantize, use sym=False. This subcommand symmetric quantization since the beginning and incorrectly reporting the model to be symmetric will use GPTQ-Marlin (which does not support asymmetric quantization).

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.

@danieldk danieldk force-pushed the feature/use-gptq-marlin-for-gptq branch 3 times, most recently from 7cbe33b to de4e0c4 Compare June 25, 2024 10:14
GPTQ-Marlin is currently the best-performing kernel for GPTQ models. So
let's use it by default if the kernels are installed, the GPU supports
it, and the kernels support the configuration.

For models generated by `text-generation-server quantize`, use
`sym=False`. This subcommand symmetric quantization since the beginning
and incorrectly reporting the model to be symmetric will use
GPTQ-Marlin (which does not support asymmetric quantization).
@danieldk danieldk force-pushed the feature/use-gptq-marlin-for-gptq branch from de4e0c4 to 2e763d1 Compare June 27, 2024 07:53
@danieldk danieldk marked this pull request as ready for review June 27, 2024 08:56
Copy link
Collaborator

@Narsil Narsil left a comment

Choose a reason for hiding this comment

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

LGTM !

@Narsil Narsil merged commit 2ce8019 into main Jul 1, 2024
9 checks passed
@Narsil Narsil deleted the feature/use-gptq-marlin-for-gptq branch July 1, 2024 10:59
glegendre01 pushed a commit that referenced this pull request Jul 2, 2024
GPTQ-Marlin is currently the best-performing kernel for GPTQ models. So
let's use it by default if the kernels are installed, the GPU supports
it, and the kernels support the configuration.

For models generated by `text-generation-server quantize`, use
`sym=False`. This subcommand symmetric quantization since the beginning
and incorrectly reporting the model to be symmetric will use
GPTQ-Marlin (which does not support asymmetric quantization).
ErikKaum pushed a commit that referenced this pull request Jul 26, 2024
GPTQ-Marlin is currently the best-performing kernel for GPTQ models. So
let's use it by default if the kernels are installed, the GPU supports
it, and the kernels support the configuration.

For models generated by `text-generation-server quantize`, use
`sym=False`. This subcommand symmetric quantization since the beginning
and incorrectly reporting the model to be symmetric will use
GPTQ-Marlin (which does not support asymmetric quantization).
yuanwu2017 pushed a commit to yuanwu2017/tgi-gaudi that referenced this pull request Sep 26, 2024
GPTQ-Marlin is currently the best-performing kernel for GPTQ models. So
let's use it by default if the kernels are installed, the GPU supports
it, and the kernels support the configuration.

For models generated by `text-generation-server quantize`, use
`sym=False`. This subcommand symmetric quantization since the beginning
and incorrectly reporting the model to be symmetric will use
GPTQ-Marlin (which does not support asymmetric quantization).
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