{"id":35898,"date":"2025-01-02T22:53:58","date_gmt":"2025-01-02T14:53:58","guid":{"rendered":"https:\/\/17aitech.com\/?p=35898"},"modified":"2025-01-23T17:11:13","modified_gmt":"2025-01-23T09:11:13","slug":"%e3%80%90%e6%a8%a1%e5%9e%8b%e9%83%a8%e7%bd%b2%e3%80%91%e5%9c%a8%e8%b6%8b%e5%8a%a8%e4%ba%91%e4%b8%8a%e4%bd%bf%e7%94%a8vllm%e9%83%a8%e7%bd%b2%e5%af%b9%e8%af%9d%e6%a8%a1%e5%9e%8b%e5%92%8cembedding","status":"publish","type":"post","link":"https:\/\/17aitech.com\/?p=35898","title":{"rendered":"\u3010\u6a21\u578b\u90e8\u7f72\u3011\u5728\u8d8b\u52a8\u4e91\u4e0a\u4f7f\u7528vllm\u90e8\u7f72\u6a21\u578b"},"content":{"rendered":"<div id=\"ez-toc-container\" class=\"ez-toc-v2_0_78 ez-toc-wrap-left-text counter-hierarchy ez-toc-counter ez-toc-light-blue ez-toc-container-direction\">\n<div class=\"ez-toc-title-container\">\n<p class=\"ez-toc-title\" style=\"cursor:inherit\">\u6587\u7ae0\u76ee\u5f55<\/p>\n<span class=\"ez-toc-title-toggle\"><a href=\"#\" class=\"ez-toc-pull-right ez-toc-btn ez-toc-btn-xs ez-toc-btn-default ez-toc-toggle\" aria-label=\"Toggle Table of Content\"><span class=\"ez-toc-js-icon-con\"><span class=\"\"><span class=\"eztoc-hide\" style=\"display:none;\">Toggle<\/span><span class=\"ez-toc-icon-toggle-span\"><svg style=\"fill: #999;color:#999\" xmlns=\"http:\/\/www.w3.org\/2000\/svg\" class=\"list-377408\" width=\"20px\" height=\"20px\" viewBox=\"0 0 24 24\" fill=\"none\"><path d=\"M6 6H4v2h2V6zm14 0H8v2h12V6zM4 11h2v2H4v-2zm16 0H8v2h12v-2zM4 16h2v2H4v-2zm16 0H8v2h12v-2z\" fill=\"currentColor\"><\/path><\/svg><svg style=\"fill: #999;color:#999\" class=\"arrow-unsorted-368013\" xmlns=\"http:\/\/www.w3.org\/2000\/svg\" width=\"10px\" height=\"10px\" viewBox=\"0 0 24 24\" version=\"1.2\" baseProfile=\"tiny\"><path d=\"M18.2 9.3l-6.2-6.3-6.2 6.3c-.2.2-.3.4-.3.7s.1.5.3.7c.2.2.4.3.7.3h11c.3 0 .5-.1.7-.3.2-.2.3-.5.3-.7s-.1-.5-.3-.7zM5.8 14.7l6.2 6.3 6.2-6.3c.2-.2.3-.5.3-.7s-.1-.5-.3-.7c-.2-.2-.4-.3-.7-.3h-11c-.3 0-.5.1-.7.3-.2.2-.3.5-.3.7s.1.5.3.7z\"\/><\/svg><\/span><\/span><\/span><\/a><\/span><\/div>\n<nav><ul class='ez-toc-list ez-toc-list-level-1 ' ><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-1\" href=\"https:\/\/17aitech.com\/?p=35898\/#%E5%89%8D%E8%A8%80\" >\u524d\u8a00<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-2\" href=\"https:\/\/17aitech.com\/?p=35898\/#vllm%E7%AE%80%E4%BB%8B\" >vllm\u7b80\u4ecb<\/a><ul class='ez-toc-list-level-3' ><li class='ez-toc-heading-level-3'><a class=\"ez-toc-link ez-toc-heading-3\" href=\"https:\/\/17aitech.com\/?p=35898\/#vllm%E5%AE%98%E7%BD%91\" >vllm\u5b98\u7f51<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-3'><a class=\"ez-toc-link ez-toc-heading-4\" href=\"https:\/\/17aitech.com\/?p=35898\/#vllm%E7%8E%AF%E5%A2%83%E4%BE%9D%E8%B5%96\" >vllm\u73af\u5883\u4f9d\u8d56<\/a><\/li><\/ul><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-5\" href=\"https:\/\/17aitech.com\/?p=35898\/#%E7%8E%AF%E5%A2%83%E5%87%86%E5%A4%87\" >\u73af\u5883\u51c6\u5907<\/a><ul class='ez-toc-list-level-3' ><li class='ez-toc-heading-level-3'><a class=\"ez-toc-link ez-toc-heading-6\" href=\"https:\/\/17aitech.com\/?p=35898\/#%E9%80%89%E6%8B%A9%E9%95%9C%E5%83%8F\" >\u9009\u62e9\u955c\u50cf<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-3'><a class=\"ez-toc-link ez-toc-heading-7\" href=\"https:\/\/17aitech.com\/?p=35898\/#%E5%AE%89%E8%A3%85vllm\" >\u5b89\u88c5vllm<\/a><\/li><\/ul><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-8\" href=\"https:\/\/17aitech.com\/?p=35898\/#%E9%83%A8%E7%BD%B2%E5%AF%B9%E8%AF%9D%E6%A8%A1%E5%9E%8B\" >\u90e8\u7f72\u5bf9\u8bdd\u6a21\u578b<\/a><ul class='ez-toc-list-level-3' ><li class='ez-toc-heading-level-3'><a class=\"ez-toc-link ez-toc-heading-9\" href=\"https:\/\/17aitech.com\/?p=35898\/#%E4%B8%8B%E8%BD%BD%E6%A8%A1%E5%9E%8B\" >\u4e0b\u8f7d\u6a21\u578b<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-3'><a class=\"ez-toc-link ez-toc-heading-10\" href=\"https:\/\/17aitech.com\/?p=35898\/#%E5%90%AF%E5%8A%A8vllm\" >\u542f\u52a8vllm<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-3'><a class=\"ez-toc-link ez-toc-heading-11\" href=\"https:\/\/17aitech.com\/?p=35898\/#%E7%AB%AF%E5%8F%A3%E6%98%A0%E5%B0%84\" >\u7aef\u53e3\u6620\u5c04<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-3'><a class=\"ez-toc-link ez-toc-heading-12\" href=\"https:\/\/17aitech.com\/?p=35898\/#%E8%B0%83%E7%94%A8%E9%AA%8C%E8%AF%81\" >\u8c03\u7528\u9a8c\u8bc1<\/a><\/li><\/ul><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-13\" href=\"https:\/\/17aitech.com\/?p=35898\/#%E9%83%A8%E7%BD%B2embedding%E6%A8%A1%E5%9E%8B\" >\u90e8\u7f72embedding\u6a21\u578b<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-14\" href=\"https:\/\/17aitech.com\/?p=35898\/#%E5%B8%B8%E8%A7%81%E9%97%AE%E9%A2%98%EF%BC%9A\" >\u5e38\u89c1\u95ee\u9898\uff1a<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-15\" href=\"https:\/\/17aitech.com\/?p=35898\/#%E8%AF%A5%E7%B3%BB%E5%88%97%E6%96%87%E7%AB%A0\" >\u8be5\u7cfb\u5217\u6587\u7ae0<\/a><\/li><\/ul><\/nav><\/div>\n<h2><span class=\"ez-toc-section\" id=\"%E5%89%8D%E8%A8%80\"><\/span>\u524d\u8a00<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p>\u672c\u6587\u5c06\u4ecb\u7ecd\u5982\u4f55\u5728\u8d8b\u52a8\u4e91\u5e73\u53f0\u4e0a\u4f7f\u7528vllm\u90e8\u7f72Qwen2-0.5B-Instruct\u5bf9\u8bdd\u6a21\u578b\u548cBGE\u5411\u91cf\u5316\u6a21\u578b\uff0c\u5b9e\u73b0\u9ad8\u6027\u80fd\u7684\u6a21\u578b\u670d\u52a1\u3002<\/p>\n<h2><span class=\"ez-toc-section\" id=\"vllm%E7%AE%80%E4%BB%8B\"><\/span>vllm\u7b80\u4ecb<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<h3><span class=\"ez-toc-section\" id=\"vllm%E5%AE%98%E7%BD%91\"><\/span>vllm\u5b98\u7f51<span class=\"ez-toc-section-end\"><\/span><\/h3>\n<p>\u5b89\u88c5\u8bf4\u660e\uff1a<a href=\"https:\/\/docs.vllm.ai\/en\/latest\/getting_started\/installation.html\">https:\/\/docs.vllm.ai\/en\/latest\/getting_started\/installation.html<\/a><\/p>\n<h3><span class=\"ez-toc-section\" id=\"vllm%E7%8E%AF%E5%A2%83%E4%BE%9D%E8%B5%96\"><\/span>vllm\u73af\u5883\u4f9d\u8d56<span class=\"ez-toc-section-end\"><\/span><\/h3>\n<p>\u5b98\u65b9\u5efa\u8bae\uff1a<\/p>\n<ul>\n<li>Python 3.12<\/li>\n<li>CUDA 12.1<\/li>\n<\/ul>\n<h2><span class=\"ez-toc-section\" id=\"%E7%8E%AF%E5%A2%83%E5%87%86%E5%A4%87\"><\/span>\u73af\u5883\u51c6\u5907<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<h3><span class=\"ez-toc-section\" id=\"%E9%80%89%E6%8B%A9%E9%95%9C%E5%83%8F\"><\/span>\u9009\u62e9\u955c\u50cf<span class=\"ez-toc-section-end\"><\/span><\/h3>\n<ol>\n<li>\u9009\u62e9\u955c\u50cf\u73af\u5883<br \/>\n\u56e0\u4e3a\u8d8b\u52a8\u4e91\u4e2d\u901a\u8fc7<code>pip install vllm<\/code>\u4f1a\u62a5\u9519\uff0c\u6240\u4ee5\u6211\u4eec\u5728\u542f\u52a8\u5bb9\u5668\u65f6\uff0c\u9009\u62e9\u5df2\u7ecf\u96c6\u6210vllm\u7684\u955c\u50cf\u3002<br \/>\n<a href=\"https:\/\/17aitech.com\/wp-content\/uploads\/2025\/01\/\u8d8b\u52a8\u4e91\u955c\u50cf\u9009\u62e9.png\" data-fancybox=\"images\" data-fancybox=\"gallery\"><img decoding=\"async\" src=\"https:\/\/17aitech.com\/wp-content\/uploads\/2025\/01\/\u8d8b\u52a8\u4e91\u955c\u50cf\u9009\u62e9.png\" alt=\"\" \/><\/a><\/li>\n<\/ol>\n<h3><span class=\"ez-toc-section\" id=\"%E5%AE%89%E8%A3%85vllm\"><\/span>\u5b89\u88c5vllm<span class=\"ez-toc-section-end\"><\/span><\/h3>\n<p>(\u56e0\u4e3a\u955c\u50cf\u4e2d\u5df2\u7ecf\u96c6\u6210vllm\uff0c\u6240\u4ee5\u6b64\u5904\u7565\u8fc7)<\/p>\n<h2><span class=\"ez-toc-section\" id=\"%E9%83%A8%E7%BD%B2%E5%AF%B9%E8%AF%9D%E6%A8%A1%E5%9E%8B\"><\/span>\u90e8\u7f72\u5bf9\u8bdd\u6a21\u578b<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<h3><span class=\"ez-toc-section\" id=\"%E4%B8%8B%E8%BD%BD%E6%A8%A1%E5%9E%8B\"><\/span>\u4e0b\u8f7d\u6a21\u578b<span class=\"ez-toc-section-end\"><\/span><\/h3>\n<p><strong>\u65b9\u5f0f\u4e00<\/strong>\uff1a\u9009\u62e9\u5176\u4ed6\u4eba\u4e0a\u4f20\u5e76\u516c\u5f00\u7684\u6a21\u578b\u3002<br \/>\n\u5728\u542f\u52a8\u9879\u76ee\u65f6\uff0c\u9009\u62e9\u6a21\u578b\u52a0\u8f7d\uff0c\u5728\u8d8b\u52a8\u4e91\u7684\u516c\u5171\u6a21\u578b\u4e2d\u9009\u62e9<code>Qwen2.5-0.5B-Instruct<\/code>\u6a21\u578b\u3002<\/p>\n<p><strong>\u65b9\u5f0f\u4e8c<\/strong>\uff1a\u81ea\u5df1\u4e0b\u8f7d\u6a21\u578b\u3002<\/p>\n<p>\u5207\u6362\u81f3<code>\/gemini\/code<\/code>\u76ee\u5f55\u4e0b\uff0c\u4e0b\u8f7d\u6a21\u578b\uff1a<\/p>\n<pre><code class=\"language-bash\">git lfs install\ngit clone https:\/\/www.modelscope.cn\/Qwen\/Qwen2.5-0.5B-Instruct.git<\/code><\/pre>\n<p>\u8865\u5145\u8bf4\u660e\uff1a<\/p>\n<ul>\n<li>\u6b64\u5904\u6a21\u578b\u4e5f\u53ef\u4ee5\u4f7f\u7528\u8d8b\u52a8\u4e91\u7684<a href=\"https:\/\/platform.virtaicloud.com\/gemini\/v1\/gemini_doc\/02-%E6%93%8D%E4%BD%9C%E6%8C%87%E5%8D%97\/03-%E6%A8%A1%E5%9E%8B\/01-%E4%B8%8A%E4%BC%A0%E6%A8%A1%E5%9E%8B.html#%E5%88%9B%E5%BB%BA%E6%A8%A1%E5%9E%8B%E9%9B%86\">\u6a21\u578b\u4e0a\u4f20<\/a>\u529f\u80fd\uff0c\u56e0\u4e3a\u7bc7\u5e45\u9650\u5236\uff0c\u6b64\u5904\u7565\u8fc7\u3002<\/li>\n<\/ul>\n<h3><span class=\"ez-toc-section\" id=\"%E5%90%AF%E5%8A%A8vllm\"><\/span>\u542f\u52a8vllm<span class=\"ez-toc-section-end\"><\/span><\/h3>\n<p>\u4f7f\u7528\u4ee5\u4e0b\u547d\u4ee4\u542f\u52a8vllm\u670d\u52a1\uff1a<\/p>\n<pre><code class=\"language-bash\">python -m vllm.entrypoints.openai.api_server --model Qwen2.5-0.5B-Instruct --host 0.0.0.0 --port 8000<\/code><\/pre>\n<p>\u8fd0\u884c\u7ed3\u679c\uff1a<br \/>\n<a href=\"https:\/\/17aitech.com\/wp-content\/uploads\/2025\/01\/vllm\u542f\u52a8\u622a\u56fe.png\" data-fancybox=\"images\" data-fancybox=\"gallery\"><img decoding=\"async\" src=\"https:\/\/17aitech.com\/wp-content\/uploads\/2025\/01\/vllm\u542f\u52a8\u622a\u56fe.png\" alt=\"\" \/><\/a><\/p>\n<p>\u6ce8\u610f\u4e8b\u9879\uff1a<\/p>\n<ul>\n<li>\u542f\u52a8<code>vllm<\/code>\u547d\u4ee4\u65f6\uff0c\u5b83\u4f1a\u5728\u5f53\u524d\u76ee\u5f55\u4e0b\u5bfb\u627e<code>--model<\/code>\u53c2\u6570\u6307\u5b9a\u7684\u6a21\u578b\u6587\u4ef6\u5939\uff0c\u6240\u4ee5\u8bf7\u786e\u4fdd\u5f53\u524d\u76ee\u5f55\u4e0b\u6709<code>Qwen2.5-0.5B-Instruct<\/code>\u6a21\u578b\u6587\u4ef6\u3002<\/li>\n<\/ul>\n<h3><span class=\"ez-toc-section\" id=\"%E7%AB%AF%E5%8F%A3%E6%98%A0%E5%B0%84\"><\/span>\u7aef\u53e3\u6620\u5c04<span class=\"ez-toc-section-end\"><\/span><\/h3>\n<p>\u5728\u8d8b\u52a8\u4e91\u63a7\u5236\u53f0\u7684\u53f3\u4fa7&quot;\u7aef\u53e3&quot;\uff0c\u6dfb\u52a0\u7aef\u53e3\u6620\u5c04\u5982\u4e0b\uff1a<br \/>\n<a href=\"https:\/\/17aitech.com\/wp-content\/uploads\/2025\/01\/\u7aef\u53e3\u6620\u5c04.png\" data-fancybox=\"images\" data-fancybox=\"gallery\"><img decoding=\"async\" src=\"https:\/\/17aitech.com\/wp-content\/uploads\/2025\/01\/\u7aef\u53e3\u6620\u5c04.png\" alt=\"\" \/><\/a><\/p>\n<h3><span class=\"ez-toc-section\" id=\"%E8%B0%83%E7%94%A8%E9%AA%8C%E8%AF%81\"><\/span>\u8c03\u7528\u9a8c\u8bc1<span class=\"ez-toc-section-end\"><\/span><\/h3>\n<pre><code class=\"language-python\">from openai import OpenAI\nopenai_api_key = &quot;EMPTY&quot;\nopenai_api_base = &quot;http:\/\/direct.virtaicloud.com:28462\/v1&quot;\n\nclient = OpenAI(\n    api_key=openai_api_key,\n    base_url=openai_api_base,\n)\n\nchat_response = client.chat.completions.create(\n    model=&quot;Qwen2.5-0.5B-Instruct&quot;,\n    messages=[\n        {&quot;role&quot;: &quot;system&quot;, &quot;content&quot;: &quot;\u4f60\u662f\u4e00\u4e2a\u5f88\u6709\u7528\u7684\u52a9\u624b\u3002&quot;},\n        {&quot;role&quot;: &quot;user&quot;, &quot;content&quot;: &quot;\u4e2d\u534e\u4eba\u6c11\u5171\u548c\u56fd\u7684\u9996\u90fd\u662f\u54ea\u91cc\uff1f&quot;},\n    ]\n)\nprint(&quot;Chat response:&quot;, chat_response)\n<\/code><\/pre>\n<p>\u8fd0\u884c\u7ed3\u679c\uff1a<br \/>\n<a href=\"https:\/\/17aitech.com\/wp-content\/uploads\/2025\/01\/langchain\u8c03\u7528vllm.png\" data-fancybox=\"images\" data-fancybox=\"gallery\"><img decoding=\"async\" src=\"https:\/\/17aitech.com\/wp-content\/uploads\/2025\/01\/langchain\u8c03\u7528vllm.png\" alt=\"\" \/><\/a><\/p>\n<p>\u6ce8\u610f\u4e8b\u9879\uff1a<\/p>\n<ul>\n<li>\u793a\u4f8b\u4e2d\uff0c\u8d8b\u52a8\u4e91\u914d\u7f6e\u7aef\u53e3\u6620\u5c04\u540e\u7684\u5916\u90e8\u5730\u5740\u4e3a\uff1a<code>direct.virtaicloud.com:28462<\/code>\uff0c\u8bfb\u8005\u9700\u8981\u6839\u636e\u5b9e\u9645\u60c5\u51b5\u4fee\u6539\u3002<\/li>\n<li>\u793a\u4f8b\u4e2d\uff0c\u90e8\u7f72\u7684\u6a21\u578b\u4e3a<code>Qwen2.5-0.5B-Instruct<\/code>\uff0c\u8bf7\u6ce8\u610f\u6839\u636e\u5b9e\u9645\u60c5\u51b5\u4fee\u6539\u3002<\/li>\n<li>\u793a\u4f8b\u4e2d\uff0c\u672c\u5730\u8c03\u7528\u4ee3\u7801\u7565\u8fc7\u4e86<code>langchain<\/code>\u5e93\u7684\u5b89\u88c5\uff0c\u8bf7\u8bb0\u5f97\u5b89\u88c5\u3002<\/li>\n<\/ul>\n<h2><span class=\"ez-toc-section\" id=\"%E9%83%A8%E7%BD%B2embedding%E6%A8%A1%E5%9E%8B\"><\/span>\u90e8\u7f72embedding\u6a21\u578b<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p>vllm\u90e8\u7f72embedding\u6a21\u578b\u5b58\u5728\u8bf8\u591a\u95ee\u9898\uff0c\u5982\uff1avllm\u652f\u6301\u7684embedding\u6a21\u578b\u6709\u9650\uff0cvllm\u7248\u672c\u66f4\u65b0\u540e\u652f\u6301\u7684\u6a21\u578b\u4e0e\u5b98\u7f51\u4e0d\u4e00\u81f4\u7b49\u7b49&#8230;<\/p>\n<p>\u56e0\u6b64\uff0cembedding\u6a21\u578b\u7684\u90e8\u7f72\u8fd8\u662f\u5efa\u8bae\u901a\u8fc7xinference\u6765\u8fdb\u884c\uff0c\u5177\u4f53\u67e5\u770b<a href=\"https:\/\/17aitech.com\/?p=33285\">Xinference\u90e8\u7f72\u5411\u91cf\u5316\u6a21\u578b<\/a><\/p>\n<h2><span class=\"ez-toc-section\" id=\"%E5%B8%B8%E8%A7%81%E9%97%AE%E9%A2%98%EF%BC%9A\"><\/span>\u5e38\u89c1\u95ee\u9898\uff1a<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p>\u95ee\u98981\uff1a\u5b89\u88c5<code>vllm<\/code>\u65f6\uff0c\u62a5\u9519<code>ERROR: Could not install packages due to an OSError: [Errno 16] Device or resource busy: &#039;libnccl.so.2&#039;<\/code><\/p>\n<p>\u95ee\u9898\u539f\u56e0\uff1a\u8be5\u95ee\u9898\u662f\u56e0\u4e3a\u5b89\u88c5<code>vllm<\/code>\u65f6\uff0c\u6709\u7a0b\u5e8f\u5360\u7528\u4e86<code>libnccl.so.2<\/code>\uff0c\u5bfc\u81f4\u5b89\u88c5\u5931\u8d25\u3002<br \/>\n\u89e3\u51b3\u65b9\u6cd5\uff1a\u6682\u65e0\u597d\u7684\u89e3\u51b3\u65b9\u6848\uff0c\u53ef\u4ee5\u6309\u7167\u6587\u7ae0\u4e2d\u7684\u955c\u50cf\uff0c\u52a0\u8f7d\u5e26\u6709<code>vllm<\/code>\u7684\u955c\u50cf\u3002<\/p>\n<p>\u95ee\u98982\uff1a\u542f\u52a8<code>vllm<\/code>\u65f6\uff0c\u63d0\u793a\u62a5\u9519\uff1a<code>OSError: We couldn&#039;t connect to &#039;https:\/\/huggingface.co&#039; to load this file<\/code><br \/>\n\u95ee\u9898\u539f\u56e0\uff1a\u8be5\u95ee\u9898\u4e00\u822c\u662f\u52a0\u8f7d\u6a21\u578b\u65f6\uff0c\u6a21\u578b\u5730\u5740\u914d\u7f6e\u9519\u8bef\u6240\u81f4\u3002<br \/>\n\u89e3\u51b3\u65b9\u6cd5\uff1a\u68c0\u67e5<code>--model <\/code>\u53c2\u6570\u7684\u6a21\u578b\u5730\u5740\u662f\u5426\u6b63\u786e\uff0c\u6216\u8005\u6a21\u578b\u662f\u5426\u5b58\u5728\u3002<\/p>\n<h2><span class=\"ez-toc-section\" id=\"%E8%AF%A5%E7%B3%BB%E5%88%97%E6%96%87%E7%AB%A0\"><\/span>\u8be5\u7cfb\u5217\u6587\u7ae0<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<ul>\n<li><a href=\"https:\/\/17aitech.com\/?p=36314\">\u3010\u6a21\u578b\u90e8\u7f72\u3011\u5728AutoDL\u4e0a\u4f7f\u7528Xinference\u90e8\u7f72\u6a21\u578b<\/a><\/li>\n<li><a href=\"https:\/\/17aitech.com\/?p=36251\">\u3010\u6a21\u578b\u8bad\u7ec3\u3011\u5728AutoDL\u4e0a\u4f7f\u7528LLamaFactory\u8fdb\u884c\u6a21\u578b\u8bad\u7ec3<\/a><\/li>\n<li><a href=\"https:\/\/17aitech.com\/?p=35939\">\u3010\u6a21\u578b\u90e8\u7f72\u3011\u5728\u8d8b\u52a8\u4e91\u4e0a\u4f7f\u7528xinference\u90e8\u7f72\u6a21\u578b<\/a><\/li>\n<li><a href=\"https:\/\/17aitech.com\/?p=35898\">\u3010\u6a21\u578b\u90e8\u7f72\u3011\u5728\u8d8b\u52a8\u4e91\u4e0a\u4f7f\u7528vllm\u90e8\u7f72\u6a21\u578b<\/a><\/li>\n<\/ul>\n","protected":false},"excerpt":{"rendered":"<p>\u524d\u8a00 \u672c\u6587\u5c06\u4ecb\u7ecd\u5982\u4f55\u5728\u8d8b\u52a8\u4e91\u5e73\u53f0\u4e0a\u4f7f\u7528v [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":36041,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"aside","meta":{"site-sidebar-layout":"default","site-content-layout":"","ast-site-content-layout":"default","site-content-style":"default","site-sidebar-style":"default","ast-global-header-display":"","ast-banner-title-visibility":"","ast-main-header-display":"","ast-hfb-above-header-display":"","ast-hfb-below-header-display":"","ast-hfb-mobile-header-display":"","site-post-title":"","ast-breadcrumbs-content":"","ast-featured-img":"","footer-sml-layout":"","theme-transparent-header-meta":"default","adv-header-id-meta":"","stick-header-meta":"default","header-above-stick-meta":"","header-main-stick-meta":"","header-below-stick-meta":"","astra-migrate-meta-layouts":"set","ast-page-background-enabled":"default","ast-page-background-meta":{"desktop":{"background-color":"var(--ast-global-color-4)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"tablet":{"background-color":"","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"mobile":{"background-color":"","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""}},"ast-content-background-meta":{"desktop":{"background-color":"var(--ast-global-color-5)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"tablet":{"background-color":"var(--ast-global-color-5)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"mobile":{"background-color":"var(--ast-global-color-5)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""}},"footnotes":""},"categories":[69],"tags":[48],"class_list":["post-35898","post","type-post","status-publish","format-aside","has-post-thumbnail","hentry","category-report","tag-48","post_format-post-format-aside"],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v26.4 - https:\/\/yoast.com\/wordpress\/plugins\/seo\/ -->\n<title>\u3010\u6a21\u578b\u90e8\u7f72\u3011\u5728\u8d8b\u52a8\u4e91\u4e0a\u4f7f\u7528vllm\u90e8\u7f72\u6a21\u578b - \u4e00\u8d77AI\u6280\u672f<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/17aitech.com\/?p=35898\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\/\/17aitech.com\/?p=35898\",\"url\":\"https:\/\/17aitech.com\/?p=35898\",\"name\":\"\u3010\u6a21\u578b\u90e8\u7f72\u3011\u5728\u8d8b\u52a8\u4e91\u4e0a\u4f7f\u7528vllm\u90e8\u7f72\u6a21\u578b - \u4e00\u8d77AI\u6280\u672f\",\"isPartOf\":{\"@id\":\"https:\/\/17aitech.com\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\/\/17aitech.com\/?p=35898#primaryimage\"},\"image\":{\"@id\":\"https:\/\/17aitech.com\/?p=35898#primaryimage\"},\"thumbnailUrl\":\"https:\/\/17aitech.com\/wp-content\/uploads\/2025\/01\/\u5c01\u9762.jpeg\",\"datePublished\":\"2025-01-02T14:53:58+00:00\",\"dateModified\":\"2025-01-23T09:11:13+00:00\",\"author\":{\"@id\":\"https:\/\/17aitech.com\/#\/schema\/person\/3d23bb6f7f115fcefc9ae7803a691739\"},\"breadcrumb\":{\"@id\":\"https:\/\/17aitech.com\/?p=35898#breadcrumb\"},\"inLanguage\":\"zh-Hans\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/17aitech.com\/?p=35898\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"zh-Hans\",\"@id\":\"https:\/\/17aitech.com\/?p=35898#primaryimage\",\"url\":\"https:\/\/17aitech.com\/wp-content\/uploads\/2025\/01\/\u5c01\u9762.jpeg\",\"contentUrl\":\"https:\/\/17aitech.com\/wp-content\/uploads\/2025\/01\/\u5c01\u9762.jpeg\",\"width\":654,\"height\":457},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/17aitech.com\/?p=35898#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"\u9996\u9875\",\"item\":\"https:\/\/17aitech.com\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"\u3010\u6a21\u578b\u90e8\u7f72\u3011\u5728\u8d8b\u52a8\u4e91\u4e0a\u4f7f\u7528vllm\u90e8\u7f72\u6a21\u578b\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/17aitech.com\/#website\",\"url\":\"https:\/\/17aitech.com\/\",\"name\":\"\u4e00\u8d77AI\u6280\u672f\",\"description\":\"\u8ba9AI\u77e5\u8bc6\u89e6\u624b\u53ef\u53ca\",\"alternateName\":\"\u4e00\u8d77AI\u6280\u672f\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/17aitech.com\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"zh-Hans\"},{\"@type\":\"Person\",\"@id\":\"https:\/\/17aitech.com\/#\/schema\/person\/3d23bb6f7f115fcefc9ae7803a691739\",\"name\":\"Dongming\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"zh-Hans\",\"@id\":\"https:\/\/17aitech.com\/#\/schema\/person\/image\/\",\"url\":\"\/\/17aitech.com\/wp-content\/uploads\/member\/avatars\/238a0b923820dcc5.1732798681.jpg\",\"contentUrl\":\"\/\/17aitech.com\/wp-content\/uploads\/member\/avatars\/238a0b923820dcc5.1732798681.jpg\",\"caption\":\"Dongming\"},\"description\":\"\u89c1\u5929\u5730\uff0c\u89c1\u4f17\u751f\uff0c\u89c1\u81ea\u5df1\u3002\",\"sameAs\":[\"http:\/\/17aitech.com\"],\"url\":\"https:\/\/17aitech.com\/?page_id=33738&user=1\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"\u3010\u6a21\u578b\u90e8\u7f72\u3011\u5728\u8d8b\u52a8\u4e91\u4e0a\u4f7f\u7528vllm\u90e8\u7f72\u6a21\u578b - \u4e00\u8d77AI\u6280\u672f","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/17aitech.com\/?p=35898","schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/17aitech.com\/?p=35898","url":"https:\/\/17aitech.com\/?p=35898","name":"\u3010\u6a21\u578b\u90e8\u7f72\u3011\u5728\u8d8b\u52a8\u4e91\u4e0a\u4f7f\u7528vllm\u90e8\u7f72\u6a21\u578b - \u4e00\u8d77AI\u6280\u672f","isPartOf":{"@id":"https:\/\/17aitech.com\/#website"},"primaryImageOfPage":{"@id":"https:\/\/17aitech.com\/?p=35898#primaryimage"},"image":{"@id":"https:\/\/17aitech.com\/?p=35898#primaryimage"},"thumbnailUrl":"https:\/\/17aitech.com\/wp-content\/uploads\/2025\/01\/\u5c01\u9762.jpeg","datePublished":"2025-01-02T14:53:58+00:00","dateModified":"2025-01-23T09:11:13+00:00","author":{"@id":"https:\/\/17aitech.com\/#\/schema\/person\/3d23bb6f7f115fcefc9ae7803a691739"},"breadcrumb":{"@id":"https:\/\/17aitech.com\/?p=35898#breadcrumb"},"inLanguage":"zh-Hans","potentialAction":[{"@type":"ReadAction","target":["https:\/\/17aitech.com\/?p=35898"]}]},{"@type":"ImageObject","inLanguage":"zh-Hans","@id":"https:\/\/17aitech.com\/?p=35898#primaryimage","url":"https:\/\/17aitech.com\/wp-content\/uploads\/2025\/01\/\u5c01\u9762.jpeg","contentUrl":"https:\/\/17aitech.com\/wp-content\/uploads\/2025\/01\/\u5c01\u9762.jpeg","width":654,"height":457},{"@type":"BreadcrumbList","@id":"https:\/\/17aitech.com\/?p=35898#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"\u9996\u9875","item":"https:\/\/17aitech.com\/"},{"@type":"ListItem","position":2,"name":"\u3010\u6a21\u578b\u90e8\u7f72\u3011\u5728\u8d8b\u52a8\u4e91\u4e0a\u4f7f\u7528vllm\u90e8\u7f72\u6a21\u578b"}]},{"@type":"WebSite","@id":"https:\/\/17aitech.com\/#website","url":"https:\/\/17aitech.com\/","name":"\u4e00\u8d77AI\u6280\u672f","description":"\u8ba9AI\u77e5\u8bc6\u89e6\u624b\u53ef\u53ca","alternateName":"\u4e00\u8d77AI\u6280\u672f","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/17aitech.com\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"zh-Hans"},{"@type":"Person","@id":"https:\/\/17aitech.com\/#\/schema\/person\/3d23bb6f7f115fcefc9ae7803a691739","name":"Dongming","image":{"@type":"ImageObject","inLanguage":"zh-Hans","@id":"https:\/\/17aitech.com\/#\/schema\/person\/image\/","url":"\/\/17aitech.com\/wp-content\/uploads\/member\/avatars\/238a0b923820dcc5.1732798681.jpg","contentUrl":"\/\/17aitech.com\/wp-content\/uploads\/member\/avatars\/238a0b923820dcc5.1732798681.jpg","caption":"Dongming"},"description":"\u89c1\u5929\u5730\uff0c\u89c1\u4f17\u751f\uff0c\u89c1\u81ea\u5df1\u3002","sameAs":["http:\/\/17aitech.com"],"url":"https:\/\/17aitech.com\/?page_id=33738&user=1"}]}},"_links":{"self":[{"href":"https:\/\/17aitech.com\/index.php?rest_route=\/wp\/v2\/posts\/35898","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/17aitech.com\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/17aitech.com\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/17aitech.com\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/17aitech.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=35898"}],"version-history":[{"count":7,"href":"https:\/\/17aitech.com\/index.php?rest_route=\/wp\/v2\/posts\/35898\/revisions"}],"predecessor-version":[{"id":37162,"href":"https:\/\/17aitech.com\/index.php?rest_route=\/wp\/v2\/posts\/35898\/revisions\/37162"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/17aitech.com\/index.php?rest_route=\/wp\/v2\/media\/36041"}],"wp:attachment":[{"href":"https:\/\/17aitech.com\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=35898"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/17aitech.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=35898"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/17aitech.com\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=35898"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}