1
mirror of https://github.com/comfyanonymous/ComfyUI.git synced 2025-08-02 15:04:50 +08:00

Add another ROCm tip.

This commit is contained in:
comfyanonymous
2024-12-04 07:11:16 -05:00
parent 4e402b11c6
commit 3bed56bb13

View File

@@ -219,6 +219,8 @@ You can enable experimental memory efficient attention on pytorch 2.5 in ComfyUI
```TORCH_ROCM_AOTRITON_ENABLE_EXPERIMENTAL=1 python main.py --use-pytorch-cross-attention```
You can also try setting this env variable `PYTORCH_TUNABLEOP_ENABLED=1` which might speed things up at the cost of a very slow initial run.
# Notes
Only parts of the graph that have an output with all the correct inputs will be executed.