You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
报错信息如下:
Traceback (most recent call last):
File "/home/dev/flux/demo_gr.py", line 217, in
demo = create_demo(args.name, args.device, args.offload)
File "/home/dev/flux/demo_gr.py", line 163, in create_demo
generator = FluxGenerator(model_name, device, offload)
File "/home/dev/flux/demo_gr.py", line 33, in init
self.model, self.ae, self.t5, self.clip, self.nsfw_classifier = get_models(
File "/home/dev/flux/demo_gr.py", line 22, in get_models
model = load_flow_model(name, device="cpu" if offload else device)
File "/home/dev/flux/src/flux/util.py", line 123, in load_flow_model
sd = load_sft(ckpt_path, device=str(device))
File "/home/ps/.local/lib/python3.10/site-packages/safetensors/torch.py", line 311, in load_file
with safe_open(filename, framework="pt", device=device) as f:
OSError: No such device (os error 19)
但是torch.cuda.is_available()返回的是true
import torch
torch.cuda.is_available()
True
请教下是什么原因?感谢!
The text was updated successfully, but these errors were encountered:
报错信息如下:
Traceback (most recent call last):
File "/home/dev/flux/demo_gr.py", line 217, in
demo = create_demo(args.name, args.device, args.offload)
File "/home/dev/flux/demo_gr.py", line 163, in create_demo
generator = FluxGenerator(model_name, device, offload)
File "/home/dev/flux/demo_gr.py", line 33, in init
self.model, self.ae, self.t5, self.clip, self.nsfw_classifier = get_models(
File "/home/dev/flux/demo_gr.py", line 22, in get_models
model = load_flow_model(name, device="cpu" if offload else device)
File "/home/dev/flux/src/flux/util.py", line 123, in load_flow_model
sd = load_sft(ckpt_path, device=str(device))
File "/home/ps/.local/lib/python3.10/site-packages/safetensors/torch.py", line 311, in load_file
with safe_open(filename, framework="pt", device=device) as f:
OSError: No such device (os error 19)
但是torch.cuda.is_available()返回的是true
请教下是什么原因?感谢!
The text was updated successfully, but these errors were encountered: