You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
xinference, version 1.2.2
已经安装了qwen的 语言模型,现在准备安装Belle-distilwhisper-large-v2-zh,报错误{
"detail": "[address=0.0.0.0:22635, pid=141] GPU index 0 has been occupied with a vLLM model: qwen2.5-instruct-0, therefore cannot allocate GPU memory for a new model."
}
Running Xinference with Docker? / 是否使用 Docker 运行 Xinfernece?
docker / docker
pip install / 通过 pip install 安装
installation from source / 从源码安装
Version info / 版本信息
xinference, version 1.2.2
The command used to start Xinference / 用以启动 xinference 的命令
我直接安装官网的命令进行启动的,也是根据管网的只是进行部署的
Reproduction / 复现过程
先根据官网的教程部署qwen
部署Belle-distilwhisper-large-v2-zh模型
Expected behavior / 期待表现
能够同时安装qwen的同时,也能部署语音模型
The text was updated successfully, but these errors were encountered:
System Info / 系統信息
xinference, version 1.2.2
已经安装了qwen的 语言模型,现在准备安装Belle-distilwhisper-large-v2-zh,报错误{
"detail": "[address=0.0.0.0:22635, pid=141] GPU index 0 has been occupied with a vLLM model: qwen2.5-instruct-0, therefore cannot allocate GPU memory for a new model."
}
Running Xinference with Docker? / 是否使用 Docker 运行 Xinfernece?
Version info / 版本信息
xinference, version 1.2.2
The command used to start Xinference / 用以启动 xinference 的命令
我直接安装官网的命令进行启动的,也是根据管网的只是进行部署的
Reproduction / 复现过程
Expected behavior / 期待表现
能够同时安装qwen的同时,也能部署语音模型
The text was updated successfully, but these errors were encountered: