lllyasviel / lllyasviel/FramePack
Xformers, Flashattn, Sageattn for RTX5090
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 17.3k
- Forks
- 1.7k
- PR merge metrics
- No merged PRs in 30d
Description
Are any of these 3 even available for RTX5090? I installed cu128 torch and its working, but I cant run any of these 3. I somehow installed Sageattn but when I started generating it gave me error(something about sm_120), so I guess I installed wrong version.
Right now, without these 3, I get 3.5s/it with TeaCache, is that good? How much faster it would be with these 3?
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
The issue names no files, tests, or entry points. Start by reproducing the RTX5090 setup with cu128 PyTorch and the reported sm_120 error, then determine whether Xformers, FlashAttention, and SageAttention support this hardware; done means verified compatibility guidance and a confirmed working configuration or a documented limitation.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python, pytorch
- Domain
- machine-learning, performance
- Issue type
- Bug
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 20/100