Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

如何从CPU切换到GPU 渲染合成视频 #591

Open
1 task done
KeepMovingNo1 opened this issue Feb 18, 2025 · 0 comments
Open
1 task done

如何从CPU切换到GPU 渲染合成视频 #591

KeepMovingNo1 opened this issue Feb 18, 2025 · 0 comments
Labels
bug Something isn't working

Comments

@KeepMovingNo1
Copy link

是否已存在类似问题?

  • 我已搜索现有问题

当前行为

切换GPU 生成视频报错:webui | 2025-02-18 15:32:07 | INFO | "./app/services/subtitle.py:26": create - loading model: ./models/whisper-large-v3, device: GPU, compute_type: int8_float16
webui | 2025-02-18 15:32:07 | ERROR | "./app/services/subtitle.py:34": create - failed to load model: unsupported device GPU

虚拟机GPU信息:
nvidia-smi
Tue Feb 18 23:33:44 2025
+-----------------------------------------------------------------------------------------+
| NVIDIA-SMI 550.90.07 Driver Version: 550.90.07 CUDA Version: 12.4 |
|-----------------------------------------+------------------------+----------------------+
| 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 A10 On | 00000000:00:06.0 Off | 0 |
| 0% 32C P8 16W / 150W | 4MiB / 23028MiB | 0% Default |
| | | N/A |
+-----------------------------------------+------------------------+----------------------+

+-----------------------------------------------------------------------------------------+
| Processes: |
| GPU GI CI PID Type Process name GPU Memory |
| ID ID Usage |
|=========================================================================================|
| No running processes found |
+-----------------------------------------------------------------------------------------+

按照wiki:#171
操作修改video.py 中几处及配置添加ffmpeg_path = "/usr/bin/ffmpeg" 均未使用GPU来渲染生成视频;请问还有可能问题出在哪儿?

配置文件:

Image

video.py:
Image

预期行为

渲染合成视频时使用GPU显卡来工作

重现步骤

生成视频时无法使用GPU

堆栈追踪/日志

切换GPU 生成视频报错:webui | 2025-02-18 15:32:07 | INFO | "./app/services/subtitle.py:26": create - loading model: ./models/whisper-large-v3, device: GPU, compute_type: int8_float16
webui | 2025-02-18 15:32:07 | ERROR | "./app/services/subtitle.py:34": create - failed to load model: unsupported device GPU

Python 版本

Python 3.8.10

操作系统

ubuntu 20.04

MoneyPrinterTurbo 版本

github https://github.com/harry0703/MoneyPrinterTurbo 未注明版本

其他信息

No response

@KeepMovingNo1 KeepMovingNo1 added the bug Something isn't working label Feb 18, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
bug Something isn't working
Projects
None yet
Development

No branches or pull requests

1 participant