Requested int8 compute type, but the target device or backend do not support efficient int8 computation.

[damaainan]

打开页面，点击立即识别，报错如下：
Requested int8 compute type, but the target device or backend do not support efficient int8 computation.
应该怎么修改配置？

[okmyworld]

如果源码部署，打开 start.py，搜索 int8 ，改为 float32,然后再试试

你的显卡不支持，确保已配置好了cuda环境。可以重新升级下显卡驱动，然后重新配置cuda
https://juejin.cn/post/7318704408727519270

[okmyworld]

升级到 v0.0.5再试试

[xunaolong]

我想请问一下我用的cuda运行的，但是报如下错误，请问怎么解决
Could not load library libcudnn_ops_infer.so.8. Error: libcudnn_ops_infer.so.8: cannot open shared object file: No such file or directory
Please make sure libcudnn_ops_infer.so.8 is in your library path!
Aborted (core dumped)

[okmyworld]

view this
SYSTRAN/faster-whisper#516

cuda environ is not

[okmyworld]

or

pip install nvidia-cublas-cu11 nvidia-cudnn-cu11

[samulenzz]

or

pip install nvidia-cublas-cu11 nvidia-cudnn-cu11

还得设置好环境变量，才能奏效。来自官方readme

pip install nvidia-cublas-cu11 nvidia-cudnn-cu11

export LD_LIBRARY_PATH=`python3 -c 'import os; import nvidia.cublas.lib; import nvidia.cudnn.lib; print(os.path.dirname(nvidia.cublas.lib.__file__) + ":" + os.path.dirname(nvidia.cudnn.lib.__file__))'`