stable-diffusion-webui-forge page: http://192.168.50.4:7860 cannot be opened

[amDosion]

I run the compose file directly. Now only two pages can be opened, one is http://192.168.50.4:8888/tree?
http://192.168.50.4:1111/

But the stable-diffusion-webui-forge page: http://192.168.50.4:7860 cannot be opened,

The log shows: mkdir: cannot create directory ‘/workspace//storage/stable_diffusion’: Permission denied
Downloading 1 model(s) to /workspace//storage/stable_diffusion/models/vae...
Downloading: https://huggingface.co/stabilityai/sdxl-vae/resolve/main/sdxl_vae.safetensors

==> /var/log/supervisor/serviceportal.log <==
INFO: 192.168.50.22:0 - "GET /favicon.ico HTTP/1.1" 307 Temporary Redirect
INFO: 192.168.50.22:0 - "GET / HTTP/1.1" 200 OK

==> /var/log/provisioning.log <==

mkdir: cannot create directory ‘/workspace//storage/stable_diffusion’: Permission denied
Downloading 3 model(s) to /workspace//storage/stable_diffusion/models/esrgan...
Downloading: https://huggingface.co/ai-forever/Real-ESRGAN/resolve/main/RealESRGAN_x4.pth

Downloading: https://huggingface.co/FacehugmanIII/4x_foolhardy_Remacri/resolve/main/4x_foolhardy_Remacri.pth

Downloading: https://huggingface.co/Akumetsu971/SD_Anime_Futuristic_Armor/resolve/main/4x_NMKD-Siax_200k.pth

Python 3.10.12 (main, Feb 4 2025, 14:57:36) [GCC 11.4.0]
Version: f0.0.1-v1.7.0d
Commit hash: f53d0b42cc0ed5098dec2ab2315d8f907786e175

==> /var/log/supervisor/syncthing.log <==
[55C4V] 2025/03/20 02:01:45 INFO: Failed to acquire [::]:22999/TCP open port on NAT-PMP@172.23.0.1: getting new lease on NAT-PMP@172.23.0.1 (external port 28199 -> internal port 22999): read udp 172.23.0.2:57004->172.23.0.1:5351: recvfrom: connection refused

==> /var/log/provisioning.log <==
Traceback (most recent call last):
File "/workspace/stable-diffusion-webui-forge/launch.py", line 48, in
main()
File "/workspace/stable-diffusion-webui-forge/launch.py", line 39, in main
prepare_environment()
File "/workspace/stable-diffusion-webui-forge/modules/launch_utils.py", line 429, in prepare_environment
raise RuntimeError(
RuntimeError: Torch is not able to use GPU; add --skip-torch-cuda-test to COMMANDLINE_ARGS variable to disable this check

Provisioning complete: Web UI will start now

==> /var/log/supervisor/syncthing.log <==
[55C4V] 2025/03/20 02:01:55 INFO: Failed to acquire [::]:22000/TCP open port on NAT-PMP@172.23.0.1: getting new lease on NAT-PMP@172.23.0.1 (external port 22326 -> internal port 22000): read udp 172.23.0.2:43546->172.23.0.1:5351: recvfrom: connection refused
[55C4V] 2025/03/20 02:02:28 INFO: Listen (BEP/tcp): TLS handshake: tls: first record does not look like a TLS handshake
[55C4V] 2025/03/20 02:02:29 INFO: Listen (BEP/tcp): TLS handshake: tls: first record does not look like a TLS handshake
[55C4V] 2025/03/20 02:02:29 INFO: Listen (BEP/tcp): TLS handshake: tls: first record does not look like a TLS handshake
[55C4V] 2025/03/20 02:02:29 INFO: Listen (BEP/tcp): TLS handshake: tls: first record does not look like a TLS handshake

==> /var/log/supervisor/jupyter.log <==
[I 2025-03-20 02:02:33.602 ServerApp] 302 GET / (@192.168.50.22) 0.99ms

Is it because I need to define the variable file or modify some other location?