lllyasviel / lllyasviel/FramePack
raise ValueError(f"Unsupported CUDA architecture: {arch}") ValueError: Unsupported CUDA architecture: sm70
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 17.3k
- Forks
- 1.7k
- PR merge metrics
- No merged PRs in 30d
Description
I made a server with nvidia tesla v100 when i tried to install this package I face this following issue:
Moving DynamicSwap_HunyuanVideoTransformer3DModelPacked to cuda:0 with preserved memory: 128 GB
0%| | 0/25 [00:00
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
Reproduce the failure from webui/demo_gradio.py on the reported Tesla V100, then trace the attention call in webui/diffusers_helper/models/hunyuan_video_packed.py and the Unsupported CUDA architecture error in sageattention/core.py. Done means the project either handles this architecture during generation or clearly establishes the supported hardware limitation.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 30/100