RuntimeError: FlashAttention only supports Ampere GPUs or newer.
#11
by
pravinkarpe
- opened
Got the below error when running the model in the colab notebook.
RuntimeError: FlashAttention only supports Ampere GPUs or newer.
You may want to refer to this thread https://huggingface.co/microsoft/Phi-3-vision-128k-instruct/discussions/3
nguyenbh
changed discussion status to
closed