lllyasviel / lllyasviel/FramePack
Compatibility issue between FramePack and RTX 5090 – CUDA Error
- Dominant language
- Python
- Stars
- 17.3k
- Forks
- 1.7k
- PR merge metrics
- No merged PRs in 30d
Description
Hello everyone,
I'm currently experiencing an issue trying to run FramePack on my system equipped with an RTX 5090. Despite installing the latest PyTorch nightly build (2.8.0.dev20250501+cu128) and CUDA Toolkit 12.8, I encounter the following error during execution:
vbnet
Copier
Modifier
RuntimeError: CUDA error: no kernel image is available for execution on the device
I’ve tried several solutions, including updating NVIDIA drivers and reinstalling PyTorch with the appropriate options, but the issue persists.
My setup:
GPU: NVIDIA RTX 5090
OS: Windows 11 Pro
Python: 3.10.11
CUDA Toolkit: 12.8
PyTorch: 2.8.0.dev20250501+cu128
I’m aware that the RTX 50 series is relatively new and compatibility issues might occur. If anyone has encountered a similar problem or has suggestions to resolve this error, I’d really appreciate your help.
Thanks in advance for your support!
Contributor guide
No contributing guide indexed for this repository
Research direction
Start by reproducing FramePack execution on Windows 11 with the reported RTX 5090, Python, PyTorch nightly, and CUDA Toolkit versions, then investigate the reported "no kernel image is available" error. Done means identifying the compatibility cause and documenting or implementing a confirmed resolution for this setup.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python, pytorch
- Domain
- machine-learning, operating-systems
- Issue type
- Bug
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100