[Bug]: ForgeUI is stuck loading (Linux)

### Checklist

- [ ] The issue exists after disabling all extensions
- [X] The issue exists on a clean installation of webui
- [ ] The issue is caused by an extension, but I believe it is caused by a bug in the webui
- [X] The issue exists in the current version of the webui
- [ ] The issue has not been reported before recently
- [ ] The issue has been reported before but has not been fixed yet

### What happened?

WebUI is constantly buffering/ loading in the text prompt box. Generating doesn't seem to work. Waited 10+ mins and nothing is happening when I press generate.

### Steps to reproduce the problem

1. Install ForgeUI
2. Try to enter a prompt
3. Watch it load forever

### What should have happened?

The WebUI should've worked.

### What browsers do you use to access the UI ?

Mozilla Firefox

### Sysinfo

[sysinfo-2024-04-05-04-47.json](https://github.com/lllyasviel/stable-diffusion-webui-forge/files/14879950/sysinfo-2024-04-05-04-47.json)

### Console logs

```Shell
################################################################
Install script for stable-diffusion + Web UI
Tested on Debian 11 (Bullseye), Fedora 34+ and openSUSE Leap 15.4 or newer.
################################################################

################################################################
Running on illog user
################################################################

################################################################
Repo already cloned, using it as install directory
################################################################

################################################################
Create and activate python venv
################################################################

################################################################
Launching launch.py...
################################################################
glibc version is 2.35
Check TCMalloc: libtcmalloc_minimal.so.4
libtcmalloc_minimal.so.4 is linked with libc.so,execute LD_PRELOAD=/lib/x86_64-linux-gnu/libtcmalloc_minimal.so.4
Python 3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]
Version: f0.0.17v1.8.0rc-latest-276-g29be1da7
Commit hash: 29be1da7cf2b5dccfc70fbdd33eb35c56a31ffb7
Legacy Preprocessor init warning: Unable to install insightface automatically. Please try run `pip install insightface` manually.
Launching Web UI with arguments:
Total VRAM 6128 MB, total RAM 23940 MB
Set vram state to: NORMAL_VRAM
/home/illog/ForgeUI/stable-diffusion-webui-forge/venv/lib/python3.10/site-packages/torch/cuda/__init__.py:611: UserWarning: Can't initialize NVML
warnings.warn("Can't initialize NVML")
Device: cuda:0 AMD Radeon RX 5600 XT : native
VAE dtype: torch.float32
CUDA Stream Activated: False
Using sub quadratic optimization for cross attention, if you have memory or speed issues try using: --attention-split
ControlNet preprocessor location: /home/illog/ForgeUI/stable-diffusion-webui-forge/models/ControlNetPreprocessor
Loading weights [15012c538f] from /home/illog/ForgeUI/stable-diffusion-webui-forge/models/Stable-diffusion/realisticVisionV51_v51VAE.safetensors
2024-04-05 14:28:50,810 - ControlNet - INFO - ControlNet UI callback registered.
Running on local URL: http://127.0.0.1:7860

To create a public link, set `share=True` in `launch()`.
model_type EPS
UNet ADM Dimension 0
Using split attention in VAE
Working with z of shape (1, 4, 32, 32) = 4096 dimensions.
Using split attention in VAE
Startup time: 8.3s (prepare environment: 1.7s, import torch: 2.9s, import gradio: 0.5s, setup paths: 0.7s, other imports: 0.3s, load scripts: 1.1s, create ui: 0.4s, gradio launch: 0.7s).
extra {'cond_stage_model.clip_l.text_projection', 'cond_stage_model.clip_l.logit_scale'}
To load target model SD1ClipModel
Begin to load 1 model
[Memory Management] Current Free GPU Memory (MB) = 5923.9990234375
[Memory Management] Model Memory (MB) = 454.2076225280762
[Memory Management] Minimal Inference Memory (MB) = 1024.0
[Memory Management] Estimated Remaining GPU Memory (MB) = 4445.791400909424
Moving model(s) has taken 0.05 seconds
```

### Additional information


Start with launch.py and the attached sysinfo JSON and console logs, focusing on the Linux AMD Radeon RX 5600 XT environment and the point where generation remains loading. Reproduce the issue with the listed ForgeUI version and determine why prompt generation does not complete. Done means entering a prompt and generating an image successfully.

Written by the indexing model from the issue text.