Atinoda / text-generation-webui-docker

Docker variants of oobabooga's text-generation-webui, including pre-built images.

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Error 804

FieldOfRice opened this issue · comments

nvidia-smi display the data shown below.
After a "docker-compose up" and some downloading the messages with the error 804 are there(see below).
I'm running this inside a host running debian 12.

Seems a nvidia/torch related issue, any pointers how to resolve it?

Thu Feb  1 12:42:13 2024       
+-----------------------------------------------------------------------------+
| NVIDIA-SMI 525.125.06   Driver Version: 525.125.06   CUDA Version: 12.0     |
|-------------------------------+----------------------+----------------------+
| GPU  Name        Persistence-M| Bus-Id        Disp.A | Volatile Uncorr. ECC |
| Fan  Temp  Perf  Pwr:Usage/Cap|         Memory-Usage | GPU-Util  Compute M. |
|                               |                      |               MIG M. |
|===============================+======================+======================|
|   0  NVIDIA GeForce ...  On   | 00000000:01:00.0 Off |                  Off |
|  0%   37C    P8    12W / 450W |      6MiB / 24564MiB |      0%      Default |
|                               |                      |                  N/A |
+-------------------------------+----------------------+----------------------+
                                                                               
+-----------------------------------------------------------------------------+
| Processes:                                                                  |
|  GPU   GI   CI        PID   Type   Process name                  GPU Memory |
|        ID   ID                                                   Usage      |
|=============================================================================|
|    0   N/A  N/A      1137      G   /usr/lib/xorg/Xorg                  4MiB |
+-----------------------------------------------------------------------------+
Recreating text-generation-webui ... done
Attaching to text-generation-webui
text-generation-webui           | === Running text-generation-webui variant: 'DEFAULT' snapshot-2023-12-31 ===
text-generation-webui           | === (This version is 11 commits behind origin main) ===
text-generation-webui           | === Image build date: 2024-01-04 22:56:23 ===
text-generation-webui           | 11:39:20-264526 INFO     Starting Text generation web UI                        
text-generation-webui           | 11:39:20-266083 WARNING                                                         
text-generation-webui           |                          You are potentially exposing the web UI to the entire  
text-generation-webui           |                          internet without any access password.                  
text-generation-webui           |                          You can create one with the "--gradio-auth" flag like  
text-generation-webui           |                          this:                                                  
text-generation-webui           |                                                                                 
text-generation-webui           |                          --gradio-auth username:password                        
text-generation-webui           |                                                                                 
text-generation-webui           |                          Make sure to replace username:password with your own.  
text-generation-webui           | 11:39:20-266993 INFO     Loading the extension "gallery"                        
text-generation-webui           | ╭───────────────────── Traceback (most recent call last) ──────────────────────╮
text-generation-webui           | │ /app/server.py:254 in                                                │
text-generation-webui           | │                                                                              │
text-generation-webui           | │   253         # Launch the web UI                                            │
text-generation-webui           | │ ❱ 254         create_interface()                                             │
text-generation-webui           | │   255         while True:                                                    │
text-generation-webui           | │                                                                              │
text-generation-webui           | │ /app/server.py:133 in create_interface                                       │
text-generation-webui           | │                                                                              │
text-generation-webui           | │   132         ui_parameters.create_ui(shared.settings['preset'])  # Paramete │
text-generation-webui           | │ ❱ 133         ui_model_menu.create_ui()  # Model tab                         │
text-generation-webui           | │   134         training.create_ui()  # Training tab                           │
text-generation-webui           | │                                                                              │
text-generation-webui           | │ /app/modules/ui_model_menu.py:36 in create_ui                                │
text-generation-webui           | │                                                                              │
text-generation-webui           | │    35         for i in range(torch.cuda.device_count()):                     │
text-generation-webui           | │ ❱  36             total_mem.append(math.floor(torch.cuda.get_device_properti │
text-generation-webui           | │    37                                                                        │
text-generation-webui           | │                                                                              │
text-generation-webui           | │ /venv/lib/python3.10/site-packages/torch/cuda/__init__.py:449 in             │
text-generation-webui           | │ get_device_properties                                                        │
text-generation-webui           | │                                                                              │
text-generation-webui           | │    448     """                                                               │
text-generation-webui           | │ ❱  449     _lazy_init()  # will define _get_device_properties                │
text-generation-webui           | │    450     device = _get_device_index(device, optional=True)                 │
text-generation-webui           | │                                                                              │
text-generation-webui           | │ /venv/lib/python3.10/site-packages/torch/cuda/__init__.py:298 in _lazy_init  │
text-generation-webui           | │                                                                              │
text-generation-webui           | │    297             os.environ["CUDA_MODULE_LOADING"] = "LAZY"                │
text-generation-webui           | │ ❱  298         torch._C._cuda_init()                                         │
text-generation-webui           | │    299         # Some of the queued calls may reentrantly call _lazy_init(); │
text-generation-webui           | ╰──────────────────────────────────────────────────────────────────────────────╯
text-generation-webui           | RuntimeError: Unexpected error from cudaGetDeviceCount(). Did you run some cuda 
text-generation-webui           | functions before calling NumCudaDevices() that might have already set an error? 
text-generation-webui           | Error 804: forward compatibility was attempted on non supported HW
text-generation-webui exited with code 1

The updates should have fixed this issue. Please re-open if not.