{"id":21425,"date":"2025-01-02T16:01:31","date_gmt":"2025-01-02T08:01:31","guid":{"rendered":"https:\/\/www.aisharenet.com\/?p=21425"},"modified":"2025-02-17T16:07:07","modified_gmt":"2025-02-17T08:07:07","slug":"inference","status":"publish","type":"post","link":"https:\/\/www.kdjingpai.com\/pt\/inference\/","title":{"rendered":"Xinference\uff1a\u8f7b\u677e\u5b9e\u73b0\u5206\u5e03\u5f0fAI\u6a21\u578b\u90e8\u7f72\u548c\u670d\u52a1"},"content":{"rendered":"<p>Xorbits Inference\uff08\u7b80\u79f0Xinference\uff09\u662f\u4e00\u4e2a\u5f3a\u5927\u4e14\u591a\u529f\u80fd\u7684\u5e93\uff0c\u4e13\u6ce8\u4e8e\u4e3a\u8bed\u8a00\u6a21\u578b\u3001\u8bed\u97f3\u8bc6\u522b\u6a21\u578b\u548c\u591a\u6a21\u6001\u6a21\u578b\u63d0\u4f9b\u5206\u5e03\u5f0f\u90e8\u7f72\u548c\u670d\u52a1\u3002\u901a\u8fc7Xorbits Inference\uff0c\u7528\u6237\u53ef\u4ee5\u8f7b\u677e\u90e8\u7f72\u548c\u670d\u52a1\u81ea\u5df1\u7684\u6a21\u578b\u6216\u5185\u7f6e\u7684\u5148\u8fdb\u6a21\u578b\uff0c\u53ea\u9700\u4e00\u6761\u547d\u4ee4\u5373\u53ef\u5b8c\u6210\u3002\u65e0\u8bba\u662f\u5728\u4e91\u7aef\u3001\u672c\u5730\u670d\u52a1\u5668\uff0c\u8fd8\u662f\u5728\u4e2a\u4eba\u7535\u8111\u4e0a\uff0cXorbits Inference\u90fd\u80fd\u9ad8\u6548\u8fd0\u884c\u3002\u8be5\u5e93\u7279\u522b\u9002\u5408\u7814\u7a76\u4eba\u5458\u3001\u5f00\u53d1\u8005\u548c\u6570\u636e\u79d1\u5b66\u5bb6\uff0c\u5e2e\u52a9\u4ed6\u4eec\u5145\u5206\u53d1\u6325\u524d\u6cbfAI\u6a21\u578b\u7684\u6f5c\u529b\u3002<\/p>\n<p><img loading=\"lazy\" decoding=\"async\" class=\"aligncenter size-full wp-image-21426\" title=\"Inference\uff1a\u8f7b\u677e\u5b9e\u73b0\u5206\u5e03\u5f0fAI\u6a21\u578b\u90e8\u7f72\u548c\u670d\u52a1-1\" src=\"https:\/\/www.kdjingpai.com\/wp-content\/uploads\/2025\/02\/78f145b3140f8a3.jpg\" alt=\"Inference\uff1a\u8f7b\u677e\u5b9e\u73b0\u5206\u5e03\u5f0fAI\u6a21\u578b\u90e8\u7f72\u548c\u670d\u52a1-1\" width=\"1726\" height=\"1026\" srcset=\"https:\/\/www.kdjingpai.com\/wp-content\/uploads\/2025\/02\/78f145b3140f8a3.jpg 1726w, https:\/\/www.kdjingpai.com\/wp-content\/uploads\/2025\/02\/78f145b3140f8a3-768x457.jpg 768w\" sizes=\"auto, (max-width: 1726px) 100vw, 1726px\" \/><\/p>\n<p>&nbsp;<\/p>\n<h2>\u529f\u80fd\u5217\u8868<\/h2>\n<ul>\n<li><strong>\u5206\u5e03\u5f0f\u90e8\u7f72<\/strong>\uff1a\u652f\u6301\u5206\u5e03\u5f0f\u90e8\u7f72\u573a\u666f\uff0c\u5141\u8bb8\u5728\u591a\u4e2a\u8bbe\u5907\u6216\u673a\u5668\u4e0a\u65e0\u7f1d\u5206\u5e03\u6a21\u578b\u63a8\u7406\u4efb\u52a1\u3002<\/li>\n<li><strong>\u6a21\u578b\u670d\u52a1<\/strong>\uff1a\u7b80\u5316\u5927\u578b\u8bed\u8a00\u6a21\u578b\u3001\u8bed\u97f3\u8bc6\u522b\u6a21\u578b\u548c\u591a\u6a21\u6001\u6a21\u578b\u7684\u670d\u52a1\u8fc7\u7a0b\u3002<\/li>\n<li><strong>\u5355\u547d\u4ee4\u90e8\u7f72<\/strong>\uff1a\u901a\u8fc7\u5355\u6761\u547d\u4ee4\u5373\u53ef\u90e8\u7f72\u548c\u670d\u52a1\u6a21\u578b\uff0c\u9002\u7528\u4e8e\u5b9e\u9a8c\u548c\u751f\u4ea7\u73af\u5883\u3002<\/li>\n<li><strong>\u5f02\u6784\u786c\u4ef6\u5229\u7528<\/strong>\uff1a\u667a\u80fd\u5229\u7528\u5305\u62ecGPU\u548cCPU\u5728\u5185\u7684\u5f02\u6784\u786c\u4ef6\uff0c\u52a0\u901f\u6a21\u578b\u63a8\u7406\u4efb\u52a1\u3002<\/li>\n<li><strong>\u7075\u6d3b\u7684API\u548c\u63a5\u53e3<\/strong>\uff1a\u63d0\u4f9b\u591a\u79cd\u63a5\u53e3\u4e0e\u6a21\u578b\u4ea4\u4e92\uff0c\u652f\u6301RPC\u3001RESTful API\uff08\u517c\u5bb9OpenAI API\uff09\u3001CLI\u548cWebUI\u3002<\/li>\n<li><strong>\u5185\u7f6e\u5148\u8fdb\u6a21\u578b<\/strong>\uff1a\u5185\u7f6e\u652f\u6301\u591a\u79cd\u524d\u6cbf\u5f00\u6e90\u6a21\u578b\uff0c\u7528\u6237\u53ef\u4ee5\u76f4\u63a5\u4f7f\u7528\u8fd9\u4e9b\u6a21\u578b\u8fdb\u884c\u5b9e\u9a8c\u3002<\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n<h2>\u4f7f\u7528\u5e2e\u52a9<\/h2>\n<h3>\u5b89\u88c5\u6d41\u7a0b<\/h3>\n<ol>\n<li><strong>\u73af\u5883\u51c6\u5907<\/strong>\uff1a\u786e\u4fdd\u5df2\u5b89\u88c5Python 3.7\u6216\u66f4\u9ad8\u7248\u672c\u3002<\/li>\n<li><strong>\u5b89\u88c5Xorbits Inference<\/strong>\uff1a<\/li>\n<\/ol>\n<pre><code>   pip install xorbits-inference\r\n<\/code><\/pre>\n<ol start=\"3\">\n<li><strong>\u9a8c\u8bc1\u5b89\u88c5<\/strong>\uff1a\u5b89\u88c5\u5b8c\u6210\u540e\uff0c\u53ef\u4ee5\u901a\u8fc7\u4ee5\u4e0b\u547d\u4ee4\u9a8c\u8bc1\u5b89\u88c5\u662f\u5426\u6210\u529f\uff1a<\/li>\n<\/ol>\n<pre><code>   <a href=\"https:\/\/www.kdjingpai.com\/de\/xorbits-inference\/\">xinference<\/a> --version\r\n<\/code><\/pre>\n<h3>\u4f7f\u7528\u6307\u5357<\/h3>\n<h4>\u90e8\u7f72\u6a21\u578b<\/h4>\n<ol>\n<li><strong>\u52a0\u8f7d\u6a21\u578b<\/strong>\uff1a\u4f7f\u7528\u4ee5\u4e0b\u547d\u4ee4\u52a0\u8f7d\u9884\u8bad\u7ec3\u6a21\u578b\uff1a<\/li>\n<\/ol>\n<pre><code>   xinference load-model --model-name &lt;\u6a21\u578b\u540d\u79f0&gt;\r\n<\/code><\/pre>\n<p>\u793a\u4f8b\uff1a<\/p>\n<pre><code>   xinference load-model --model-name gpt-3\r\n<\/code><\/pre>\n<ol start=\"2\">\n<li><strong>\u542f\u52a8\u670d\u52a1<\/strong>\uff1a\u52a0\u8f7d\u6a21\u578b\u540e\uff0c\u542f\u52a8\u670d\u52a1\uff1a<\/li>\n<\/ol>\n<pre><code>   xinference serve --model-name &lt;\u6a21\u578b\u540d\u79f0&gt;\r\n<\/code><\/pre>\n<p>\u793a\u4f8b\uff1a<\/p>\n<pre><code>   xinference serve --model-name gpt-3\r\n<\/code><\/pre>\n<ol start=\"3\">\n<li><strong>\u8c03\u7528API<\/strong>\uff1a\u670d\u52a1\u542f\u52a8\u540e\uff0c\u53ef\u4ee5\u901a\u8fc7RESTful API\u8fdb\u884c\u8c03\u7528\uff1a<\/li>\n<\/ol>\n<pre><code>   curl -X POST http:\/\/localhost:8000\/predict -d '{\"input\": \"\u4f60\u597d\"}'\r\n<\/code><\/pre>\n<h4>\u4f7f\u7528\u5185\u7f6e\u6a21\u578b<\/h4>\n<p>Xorbits Inference\u5185\u7f6e\u652f\u6301\u591a\u79cd\u5148\u8fdb\u6a21\u578b\uff0c\u7528\u6237\u53ef\u4ee5\u76f4\u63a5\u4f7f\u7528\u8fd9\u4e9b\u6a21\u578b\u8fdb\u884c\u5b9e\u9a8c\u3002\u4f8b\u5982\uff1a<\/p>\n<ul>\n<li><strong>\u8bed\u8a00\u6a21\u578b<\/strong>\uff1a\u5982GPT-3\u3001BERT\u7b49\u3002<\/li>\n<li><strong>\u8bed\u97f3\u8bc6\u522b\u6a21\u578b<\/strong>\uff1a\u5982DeepSpeech\u7b49\u3002<\/li>\n<li><strong>\u591a\u6a21\u6001\u6a21\u578b<\/strong>\uff1a\u5982CLIP\u7b49\u3002<\/li>\n<\/ul>\n<h4>\u5206\u5e03\u5f0f\u90e8\u7f72<\/h4>\n<p>Xorbits Inference\u652f\u6301\u5206\u5e03\u5f0f\u90e8\u7f72\uff0c\u7528\u6237\u53ef\u4ee5\u5728\u591a\u4e2a\u8bbe\u5907\u6216\u673a\u5668\u4e0a\u65e0\u7f1d\u5206\u5e03\u6a21\u578b\u63a8\u7406\u4efb\u52a1\u3002\u5177\u4f53\u6b65\u9aa4\u5982\u4e0b\uff1a<\/p>\n<ol>\n<li><strong>\u914d\u7f6e\u5206\u5e03\u5f0f\u73af\u5883<\/strong>\uff1a\u5728\u6bcf\u4e2a\u8282\u70b9\u4e0a\u5b89\u88c5Xorbits Inference\uff0c\u5e76\u914d\u7f6e\u7f51\u7edc\u8fde\u63a5\u3002<\/li>\n<li><strong>\u542f\u52a8\u5206\u5e03\u5f0f\u670d\u52a1<\/strong>\uff1a\u5728\u4e3b\u8282\u70b9\u4e0a\u542f\u52a8\u5206\u5e03\u5f0f\u670d\u52a1\uff1a<\/li>\n<\/ol>\n<pre><code>   xinference serve --distributed --nodes &lt;\u8282\u70b9\u5217\u8868&gt;\r\n<\/code><\/pre>\n<p>\u793a\u4f8b\uff1a<\/p>\n<pre><code>   xinference serve --distributed --nodes \"node1,node2,node3\"\r\n<\/code><\/pre>\n<ol start=\"3\">\n<li><strong>\u8c03\u7528\u5206\u5e03\u5f0fAPI<\/strong>\uff1a\u4e0e\u5355\u8282\u70b9\u90e8\u7f72\u7c7b\u4f3c\uff0c\u901a\u8fc7RESTful API\u8fdb\u884c\u8c03\u7528\uff1a<\/li>\n<\/ol>\n<pre><code>   curl -X POST http:\/\/&lt;\u4e3b\u8282\u70b9IP&gt;:8000\/predict -d '{\"input\": \"\u4f60\u597d\"}'\r\n<\/code><\/pre>\n<h3>\u5e38\u89c1\u95ee\u9898<\/h3>\n<ul>\n<li><strong>\u5982\u4f55\u66f4\u65b0\u6a21\u578b\uff1f<\/strong> \u4f7f\u7528\u4ee5\u4e0b\u547d\u4ee4\u66f4\u65b0\u6a21\u578b\uff1a<\/li>\n<\/ul>\n<pre><code>  xinference update-model --model-name &lt;\u6a21\u578b\u540d\u79f0&gt;\r\n<\/code><\/pre>\n<ul>\n<li><strong>\u5982\u4f55\u67e5\u770b\u65e5\u5fd7\uff1f<\/strong> \u4f7f\u7528\u4ee5\u4e0b\u547d\u4ee4\u67e5\u770b\u670d\u52a1\u65e5\u5fd7\uff1a<\/li>\n<\/ul>\n<pre><code>  xinference logs --model-name &lt;\u6a21\u578b\u540d\u79f0&gt;<\/code><\/pre>\n","protected":false},"excerpt":{"rendered":"<p>Xorbits Inference\uff08\u7b80\u79f0Xinference\uff09\u662f\u4e00\u4e2a\u5f3a\u5927\u4e14\u591a\u529f\u80fd\u7684\u5e93\uff0c\u4e13\u6ce8\u4e8e\u4e3a\u8bed\u8a00\u6a21\u578b\u3001\u8bed\u97f3\u8bc6\u522b\u6a21\u578b\u548c\u591a\u6a21\u6001\u6a21\u578b\u63d0\u4f9b\u5206\u5e03\u5f0f\u90e8\u7f72\u548c\u670d\u52a1\u3002\u901a\u8fc7Xorbits Inference\uff0c\u7528\u6237\u53ef\u4ee5\u8f7b\u677e\u90e8\u7f72\u548c\u670d\u52a1\u81ea\u5df1\u7684\u6a21\u578b\u6216\u5185\u7f6e\u7684\u5148\u8fdb\u6a21\u578b\uff0c&#8230;<\/p>\n","protected":false},"author":1,"featured_media":61547,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[20,46],"tags":[232],"class_list":["post-21425","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-tool","category-news","tag-bendebushukaiyuanba"],"_links":{"self":[{"href":"https:\/\/www.kdjingpai.com\/pt\/wp-json\/wp\/v2\/posts\/21425","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.kdjingpai.com\/pt\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.kdjingpai.com\/pt\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.kdjingpai.com\/pt\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.kdjingpai.com\/pt\/wp-json\/wp\/v2\/comments?post=21425"}],"version-history":[{"count":0,"href":"https:\/\/www.kdjingpai.com\/pt\/wp-json\/wp\/v2\/posts\/21425\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.kdjingpai.com\/pt\/wp-json\/wp\/v2\/media\/61547"}],"wp:attachment":[{"href":"https:\/\/www.kdjingpai.com\/pt\/wp-json\/wp\/v2\/media?parent=21425"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.kdjingpai.com\/pt\/wp-json\/wp\/v2\/categories?post=21425"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.kdjingpai.com\/pt\/wp-json\/wp\/v2\/tags?post=21425"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}