Open quocti2003 opened 3 months ago
CUDA kernel errors might be asynchronously reported at some other API call,so the stacktrace below might be incorrect. For debugging consider passing CUDA_LAUNCH_BLOCKING=1. How i can fix this. I can not execute audio-gpt.py successfully.
image
Change line 1055 of audio-chatgpt.py from
audio-chatgpt.py
self.t2i = T2I(device="cuda:1")
to
self.t2i = T2I(device="cuda:0")
CUDA kernel errors might be asynchronously reported at some other API call,so the stacktrace below might be incorrect. For debugging consider passing CUDA_LAUNCH_BLOCKING=1. How i can fix this. I can not execute audio-gpt.py successfully.