search

Jackiexiao / ChatTTS-api-ui-docker

One command to run ChatTTS
https://2noise.com/
Other
47 stars 9 forks source link

Windows11 WSL2 启动的时候报No GPU found, use CPU instead #1

Closed RainSunMe closed 5 months ago

RainSunMe commented 5 months ago

Windows11 WSL2 启动的时候报No GPU found, use CPU instead，好像是CUDA的问题？ 老哥能帮看看咋整么这个，感恩

root@DESKTOP-3BO2P10:~# docker run --rm --name chat_tts  --gpus=all --ipc=host --ulimit memlock=-1 --ulimit stac
k=67108864 -p 8080:8080 -p 8501:8501 jackiexiao/chat_tts_api_ui:24.05.30
[2024-06-02 10:55:38 +0800] [8] [INFO] Starting gunicorn 22.0.0
[2024-06-02 10:55:38 +0800] [8] [INFO] Listening at: http://0.0.0.0:8080 (8)
[2024-06-02 10:55:38 +0800] [8] [INFO] Using worker: uvicorn.workers.UvicornWorker
[2024-06-02 10:55:38 +0800] [9] [INFO] Booting worker with pid: 9
2024-06-02 10:55:40.176 | INFO     | api:<module>:38 - Loading models...
INFO:ChatTTS.core:Load from local: tts_model
/opt/conda/lib/python3.10/site-packages/torch/cuda/__init__.py:118: UserWarning: CUDA initialization: Unexpected error from cudaGetDeviceCount(). Did you run some cuda functions before calling NumCudaDevices() that might have already set an error? Error 500: named symbol not found (Triggered internally at /opt/conda/conda-bld/pytorch_1712608839953/work/c10/cuda/CUDAFunctions.cpp:108.)
  return torch._C._cuda_getDeviceCount() > 0
WARNING:ChatTTS.utils.gpu_utils:No GPU found, use CPU instead
INFO:ChatTTS.core:use cpu
INFO:ChatTTS.core:vocos loaded.
INFO:ChatTTS.core:dvae loaded.
INFO:ChatTTS.core:gpt loaded.
INFO:ChatTTS.core:decoder loaded.
INFO:ChatTTS.core:tokenizer loaded.
INFO:ChatTTS.core:All initialized.
2024-06-02 10:55:43.231 | INFO     | api:<module>:42 - Models loaded, warming up...
INFO:ChatTTS.core:All initialized.
  0%|          | 0/384 [00:00<?, ?it/s]
  You can now view your Streamlit app in your browser.

  Local URL: http://localhost:8501
  Network URL: http://172.17.0.2:8501
  External URL: http://58.19.1.117:8501

  1%|▏         | 5/384 [01:03<1:20:08, 12.69s/it]
  1%|          | 18/2048 [00:00<00:49, 41.09it/s]
2024-06-02 10:56:49.036 | INFO     | api:<module>:45 - Models loaded, warming up...
INFO:ChatTTS.core:All initialized.
  1%|▏         | 5/384 [00:00<00:14, 26.80it/s]
  1%|          | 16/2048 [00:00<00:46, 43.56it/s]
2024-06-02 10:56:49.613 | INFO     | api:<module>:47 - Warmup done, ready to serve requests!
[2024-06-02 10:56:49 +0800] [9] [INFO] Started server process [9]
[2024-06-02 10:56:49 +0800] [9] [INFO] Waiting for application startup.
[2024-06-02 10:56:49 +0800] [9] [INFO] Application startup complete.

跑了下nvidia的测试，CUDA版本是12.5

root@DESKTOP-3BO2P10:~# docker run -it --rm --gpus=all nvidia/cuda:12.5.0-base-ubuntu20.04 nvidia-smi
Sun Jun  2 02:54:34 2024
+-----------------------------------------------------------------------------------------+
| NVIDIA-SMI 555.42.03              Driver Version: 555.85         CUDA Version: 12.5     |
|-----------------------------------------+------------------------+----------------------+
| 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 RTX 4070 ...    On  |   00000000:01:00.0  On |                  N/A |
|  0%   39C    P8              8W /  220W |    1782MiB /  12282MiB |      8%      Default |
|                                         |                        |                  N/A |
+-----------------------------------------+------------------------+----------------------+

+-----------------------------------------------------------------------------------------+
| Processes:                                                                              |
|  GPU   GI   CI        PID   Type   Process name                              GPU Memory |
|        ID   ID                                                               Usage      |
|=========================================================================================|
|    0   N/A  N/A        24      G   /Xwayland                                   N/A      |
+-----------------------------------------------------------------------------------------+
Jackiexiao commented 5 months ago

有点奇怪了，我找了台 window wsl 4060ti 机器无法复现你说的问题

Jackiexiao commented 5 months ago

你可以尝试一下其他类似的项目，也提供了 window docker 部署，例如 https://github.com/jianchang512/ChatTTS-ui

RainSunMe commented 5 months ago

好的，我中午回去试试