Skip to content

Conversation

@devgdovg
Copy link
Contributor

@devgdovg devgdovg commented Dec 24, 2025

Motivation

Make Nunchaku Z-Image-Turbo model able to run with Turing GPUs.

Modifications

  • Make SVDQW4A4Linear able to change dtype to torch.float16 when initializing.
  • Convert state dict dtype to torch.float16 when loading to Turing GPU.

Checklist

  • Code is formatted using Pre-Commit hooks.
  • Relevant unit tests are added in the tests directory following the guidance in Contribution Guide.
  • Documentation and example scripts in examples are updated if necessary.
  • Throughput/latency benchmarks and quality evaluations are included where applicable.
  • For reviewers: If you're only helping merge the main branch and haven't contributed code to this PR, please remove yourself as a co-author when merging.
  • Please feel free to join our Slack, Discord or WeChat to discuss your PR.

@devgdovg devgdovg force-pushed the feat/fp16_compatibility branch from 1cac51b to fadfa6d Compare December 28, 2025 07:49
@anr2me
Copy link

anr2me commented Dec 29, 2025

Nice, now we can use it on a free T4 GPUs at Kaggle/Colab 😁

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