huggingface / huggingface/candle
Stable Diffusion 3.5 Large CUDA OUT_OF_MEMORY on RTX 3090
- Dominant language
- Rust
- Stars
- 21k
- Forks
- 1.8k
- Avg merge
- 16h 42m
- Merged PRs (30d)
- 25
Description
When I run
`cargo run --example stable-diffusion-3 --release --features=cuda -- --which 3.5-large --prompt "pretty picture"`
I am get
`Error: DriverError(CUDA_ERROR_OUT_OF_MEMORY, "out of memory")`
with Stable Diffusion 3.5 Large and Turbo.
According to this chart from [stability.ai](https://stability.ai/news/introducing-stable-diffusion-3-5) they should run on an RTX 3090.
Contributor guide
No contributing guide indexed for this repository
Research direction
Start by reproducing the reported command for the stable-diffusion-3 example with the 3.5-large and Turbo models on an RTX 3090, and record the memory failure. Trace the example's model-loading and inference path to identify why the reported hardware compatibility is not met; done means the affected models run without CUDA out-of-memory on that GPU.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- rust
- Domain
- machine-learning
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 35/100