lllyasviel / lllyasviel/FramePack
FP8 models ?
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 17.3k
- Forks
- 1.7k
- PR merge metrics
- No merged PRs in 30d
Description
So I've tried to run this in Kaggle (T4 GPU) and as expected it doesn't work because:
Feature '.bf16' requires .target sm_80 or higher
Feature 'cvt with .f32.bf16' requires .target sm_80 or higher
Is there a chance to have the models quantized in FP8 so that it can be used be people like me ?
Thanks
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
No files, tests, or entry points are named. Start by reproducing the reported failure on a Kaggle T4 and reviewing how FramePack loads its models and precision settings. Done means providing FP8-compatible models or a documented feasibility result that allows the intended hardware to run them.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 30/100