autodl上使用xinference加载qwen2-72b-instruct模型，运行不起来

[qq745639151]

System Info / 系統信息

我创建的虚拟环境，Python版本用的是3.11.9

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

The command used to start Xinference / 用以启动 xinference 的命令

xinference-local --host 0.0.0.0 --port 9997

Reproduction / 复现过程

注册模型，参数如下：
{
"version": 1,
"context_length": 30720,
"model_name": "qwen2-72b-instruct",
"model_lang": [
"en",
"zh"
],
"model_ability": [
"generate",
"chat",
"vision"
],
"model_description": "This is a custom model description.",
"model_family": "qwen2-instruct",
"model_specs": [
{
"model_format": "pytorch",
"model_size_in_billions": 72,
"quantizations": [
"none"
],
"model_id": null,
"model_hub": "huggingface",
"model_uri": "/root/autodl-tmp/xinfhome/Qwen2-72B-Instruct",
"model_revision": null
}
],
"prompt_style": {
"style_name": "QWEN",
"system_prompt": "You are a helpful assistant.",
"roles": [
"user",
"assistant"
],
"intra_message_sep": "\n",
"inter_message_sep": "",
"stop": [
"<|endoftext|>",
"<|im_start|>",
"<|im_end|>"
],
"stop_token_ids": [
151643,
151644,
151645
]
},
"is_builtin": false
}

启动模型：
然后就一直等待，但是一直运行不起来，查看日志，日志也停在这里，如下图所示：

网页上如下图所示：

Expected behavior / 期待表现

希望能把模型运行起来

[qinxuye]

vllm 降到 0.4.2 看下。