Spaces:
Running
on
Zero
Running
on
Zero
Cuda error
#2
by
Mezigore
- opened
Error
Failed to generate text: FlashAttention2 has been toggled on, but it cannot be used due to the following error: Flash Attention 2 is not available on CPU. Please make sure torch can access a CUDA device.
From the page, it seems that the model is built on a CPU device. Has anyone tried running the Gradio app on a local machine with a GPU?
It is fixed. Try it now!
teowu
changed discussion status to
closed