{"id":18916,"date":"2023-01-11T11:32:12","date_gmt":"2023-01-11T03:32:12","guid":{"rendered":"https:\/\/www.ioiotimes.com\/?p=18916"},"modified":"2023-01-11T11:32:14","modified_gmt":"2023-01-11T03:32:14","slug":"%e6%9c%80%e7%b6%a0%e8%89%b2%e7%92%b0%e4%bf%9d%e7%9a%84%e4%b8%80%e4%bb%a3%ef%bc%9anvidia%e3%80%81intel-%e5%8f%8a%e5%90%88%e4%bd%9c%e5%a4%a5%e4%bc%b4%e5%90%88%e4%bd%9c%e5%8a%a9%e5%8a%9b%e6%8f%90","status":"publish","type":"post","link":"https:\/\/www.ioiotimes.com\/?p=18916","title":{"rendered":"\u6700\u7da0\u8272\u74b0\u4fdd\u7684\u4e00\u4ee3\uff1aNVIDIA\u3001Intel\u00a0\u53ca\u5408\u4f5c\u5925\u4f34\u5408\u4f5c\u52a9\u529b\u63d0\u9ad8\u4eba\u5de5\u667a\u6167\u904b\u7b97\u6548\u7387"},"content":{"rendered":"\n

\u642d\u914d\u7b2c\u56db\u4ee3\u00a0Intel Xeon\u00a0\u53ef\u64f4\u5145\u8655\u7406\u5668\u7684\u00a0NVIDIA Hopper\u00a0\u52a0\u901f\u7cfb\u7d71\uff0c\u5305\u62ec\u00a0DGX H100\u00a0\u53ca\u4f86\u81ea\u00a0NVIDIA\u00a0\u5408\u4f5c\u5925\u4f34\u7684\u516d\u5341\u591a\u6b3e\u7cfb\u7d71\uff0c\u5176\u57f7\u884c\u6548\u7387\u8f03\u50b3\u7d71\u8cc7\u6599\u4e2d\u5fc3\u4f3a\u670d\u5668\u9ad8\u51fa\u00a025\u00a0\u500d\uff0c\u5927\u5e45\u7bc0\u7701\u80fd\u6e90\u6210\u672c<\/h2>\n\n\n\n
\"\"<\/figure>\n\n\n\n

<\/p>\n\n\n\n

\u5728\u4eba\u985e\u63a8\u52d5\u5404\u9805\u6539\u5beb\u6642\u4ee3\u7684\u985b\u8986\u6027\u5275\u65b0\u9805\u76ee\u4e2d\uff0c\u4eba\u5de5\u667a\u6167\u00a0(AI)\u00a0\u662f\u7576\u4e2d\u7684\u6838\u5fc3 \u2013 \u4ee5\u524d\u6240\u672a\u6709\u7684\u901f\u5ea6\u958b\u767c\u65b0\u51a0\u75c5\u6bd2\u00a0(COVID)\u00a0\u75ab\u82d7\u53ca\u8a3a\u65b7\u764c\u75c7\uff0c\u518d\u5230\u652f\u63f4\u81ea\u52d5\u99d5\u99db\u8eca\u548c\u77ad\u89e3\u6c23\u5019\u8b8a\u9077\u3002<\/p>\n\n\n\n

\u5e7e\u4e4e\u5404\u884c\u5404\u696d\u90fd\u80fd\u53d7\u60e0\u65bc\u63a1\u7528 AI\uff0c\u4f46\u96a8\u8457\u795e\u7d93\u7db2\u8def\u65e5\u6f38\u8b8a\u5f97\u8907\u96dc\uff0cAI \u6280\u8853\u4e5f\u9700\u8981\u6975\u70ba\u9f90\u5927\u5bc6\u96c6\u7684\u8cc7\u6e90\u3002\u70ba\u907f\u514d\u56e0\u904b\u884c\u9019\u985e\u904b\u7b97\u57fa\u790e\u8a2d\u65bd\uff0c\u800c\u5c0d\u767c\u96fb\u9020\u6210\u9700\u7d22\u7121\u5ea6\u7684\u60c5\u6cc1\uff0c\u5fc5\u9808\u76e1\u91cf\u63d0\u9ad8\u5e95\u5c64\u57fa\u790e\u6280\u8853\u7684\u904b\u884c\u6548\u7387\u3002<\/p>\n\n\n\n

\u5728 NVIDIA GPU \u548c NVIDIA AI \u5e73\u53f0\u7684\u652f\u63f4\u4e0b\uff0c\u52a0\u901f\u904b\u7b97\u7684\u6548\u7387\u63d0\u9ad8\uff0c\u4f7f\u8cc7\u6599\u4e2d\u5fc3\u80fd\u5920\u6301\u7e8c\u63a8\u52d5\u53d6\u5f97\u66f4\u65b0\u4e00\u4ee3\u7684\u7a81\u7834\u6027\u6210\u679c\u3002<\/p>\n\n\n\n

\u73fe\u96a8\u8457 Intel \u63a8\u51fa\u7b2c\u56db\u4ee3 Xeon \u53ef\u64f4\u5145\u8655\u7406\u5668\uff0cNVIDIA \u53ca\u5176\u5408\u4f5c\u5925\u4f34\u5df2\u958b\u59cb\u70ba\u9ad8\u80fd\u6548 AI \u6253\u9020\u65b0\u4e00\u4ee3\u7684\u52a0\u901f\u904b\u7b97\u7cfb\u7d71\u3002\u9019\u4e9b\u7cfb\u7d71\u642d\u8f09 NVIDIA H100 Tensor Core GPU<\/a>\uff0c\u80fd\u5920\u63d0\u4f9b\u8f03\u4e0a\u4e00\u4ee3\u7522\u54c1\u66f4\u51fa\u8272\u7684\u904b\u884c\u6548\u80fd\u3001\u66f4\u4f73\u7684\u64f4\u5145\u6027\u53ca\u66f4\u9ad8\u7684\u57f7\u884c\u6548\u7387\uff0c\u6bcf\u74e6\u6709\u66f4\u4eae\u773c\u7684\u904b\u7b97\u8868\u73fe\u53ca\u89e3\u6c7a\u554f\u984c\u7684\u80fd\u529b\u3002<\/p>\n\n\n\n

NVIDIA DGX H100\u00a0\u7cfb\u7d71<\/a>\u53ca\u7531\u00a0NVIDIA\u00a0\u5168\u7403\u5408\u4f5c\u5925\u4f34\u63a8\u51fa\u7684\u516d\u5341\u9918\u6b3e\u642d\u8f09\u00a0H100 GPU\u00a0\u7684\u4f3a\u670d\u5668\u7522\u54c1\uff0c\u90fd\u5c07\u642d\u8f09\u00a0Intel\u00a0\u7684\u65b0\u6b3e\u00a0CPU\u3002<\/p>\n\n\n\n

<\/p>\n\n\n\n

\u63d0\u9ad8\u4f01\u696d AI \u7684\u904b\u884c\u901f\u5ea6\u3001\u6548\u7387\u548c\u7bc0\u7701\u6210\u672c<\/strong><\/h3>\n\n\n\n

\u9019\u4e9b\u5373\u5c07\u63a8\u51fa\u4e26\u642d\u8f09 NVIDIA \u53ca Intel \u7522\u54c1\u7684\u7cfb\u7d71\uff0c\u5c07\u5354\u52a9\u4f01\u696d\u904b\u884c\u5404\u9805\u4f5c\u696d\u8ca0\u8f09\uff0c\u5176\u6548\u7387\u6bd4\u50c5\u642d\u8f09 CPU \u7684\u50b3\u7d71\u8cc7\u6599\u4e2d\u5fc3\u4f3a\u670d\u5668\u5e73\u5747\u9ad8\u51fa 25 \u500d\u3002\u5982\u6b64\u512a\u7570\u7684\u6bcf\u74e6\u6548\u80fd\u4ee3\u8868\u5b8c\u6210\u5de5\u4f5c\u6240\u9700\u7684\u96fb\u529b\u66f4\u5c11\uff0c\u9019\u6709\u52a9\u65bc\u78ba\u4fdd\u8b93\u8cc7\u6599\u4e2d\u5fc3\u76e1\u91cf\u9ad8\u6548\u904b\u7528\u96fb\u529b\u4f86\u5b8c\u6210\u6700\u91cd\u8981\u7684\u5de5\u4f5c\u3002<\/p>\n\n\n\n

\u8207\u524d\u4e00\u4ee3\u52a0\u901f\u7cfb\u7d71\u76f8\u6bd4\uff0c\u65b0\u4e00\u4ee3\u7684\u00a0NVIDIA\u00a0\u52a0\u901f\u4f3a\u670d\u5668\u5c07\u8a13\u7df4\u901f\u5ea6\u548c\u63a8\u8ad6\u7684\u80fd\u6e90\u4f7f\u7528\u6548\u7387<\/a>\u63d0\u9ad8\u00a03.5\u00a0\u500d\uff0c\u9019\u9ebc\u4e00\u4f86\u4fbf\u80fd\u771f\u6b63\u964d\u4f4e\u6210\u672c\uff0cAI\u00a0\u8cc7\u6599\u4e2d\u5fc3\u7684\u7e3d\u6301\u6709\u6210\u672c\u964d\u4f4e\u00a03\u00a0\u500d\u4ee5\u4e0a\u3002<\/p>\n\n\n\n

<\/p>\n\n\n\n

\u65b0\u6b3e\u7b2c\u56db\u4ee3 <\/strong>Intel Xeon <\/strong>CPU <\/strong>\u53ef\u79fb\u52d5\u66f4\u591a\u8cc7\u6599\uff0c\u52a0\u901f\u57f7\u884c NVIDIA \u7684 AI \u6280\u8853<\/strong><\/h3>\n\n\n\n

\u5168\u65b0\u7b2c\u56db\u4ee3 Intel Xeon CPU \u7684\u7279\u8272\u4e4b\u4e00\u4fbf\u662f\u652f\u63f4 PCIe Gen 5 \u898f\u683c\uff0c\u53ef\u4ee5\u5c07 CPU \u5230 NVIDIA GPU \u53ca\u7db2\u8def\u7684\u8cc7\u6599\u50b3\u8f38\u901f\u7387\u63d0\u9ad8\u4e00\u500d\u3002\u65b0\u589e\u7684 PCIe \u901a\u9053\u8b93\u6bcf\u53f0\u4f3a\u670d\u5668\u5167\u53ef\u4ee5\u90e8\u7f72\u66f4\u9ad8\u5bc6\u5ea6\u7684 GPU \u548c\u9ad8\u901f\u7db2\u8def\u3002<\/p>\n\n\n\n

\u66f4\u9ad8\u901f\u7684\u8a18\u61b6\u9ad4\u983b\u5bec\u4e5f\u63d0\u9ad8\u8655\u7406 AI \u7b49\u8cc7\u6599\u5bc6\u96c6\u578b\u4f5c\u696d\u8ca0\u8f09\u7684\u8868\u73fe\uff0c\u800c\u6bcf\u500b\u9023\u63a5\u9ad8\u9054\u6bcf\u79d2 400 GB (Gbps) \u7684\u7db2\u8def\u901f\u5ea6\uff0c\u5247\u662f\u8b93\u4f3a\u670d\u5668\u8207\u5132\u5b58\u88dd\u7f6e\u4e4b\u9593\u80fd\u66f4\u5feb\u50b3\u8f38\u8cc7\u6599\u3002<\/p>\n\n\n\n

\u642d\u8f09\u00a0H100 PCIe GPU\u00a0\u7684\u00a0NVIDIA DGX H100\u00a0\u7cfb\u7d71\u53ca\u00a0NVIDIA\u00a0\u5408\u4f5c\u5925\u4f34\u7684\u4f3a\u670d\u5668\u7522\u54c1\uff0c\u90fd\u6709\u00a0NVIDIA AI Enterprise<\/a>\u00a0\u7684\u4f7f\u7528\u6388\u6b0a\uff0cNVIDIA AI Enterprise\u00a0\u662f\u4e00\u6b3e\u63a1\u7528\u7aef\u5c0d\u7aef\u6280\u8853\u4e14\u5b89\u5168\u7684\u96f2\u7aef\u539f\u751f\u00a0AI\u00a0\u958b\u767c\u548c\u90e8\u7f72\u8edf\u9ad4\uff0c\u70ba\u9ad8\u6548\u958b\u767c\u4f01\u696d\u00a0AI\u00a0\u63d0\u4f9b\u4e00\u500b\u5b8c\u6574\u7684\u5353\u8d8a\u5e73\u53f0\u3002<\/p>\n\n\n\n

<\/p>\n\n\n\n

NVIDIA DGX H100 <\/strong>\u7cfb\u7d71\u63d0\u9ad8\u8d85\u5927\u578b AI \u8a2d\u65bd\u7684\u904b\u884c\u6548\u7387<\/strong><\/h3>\n\n\n\n

NVIDIA DGX H100 \u662f\u5168\u7403\u9996\u6b3e\u5c08\u7528 AI \u57fa\u790e\u8a2d\u65bd\u7b2c\u56db\u4ee3\u7522\u54c1\uff0c\u5728\u52a0\u901f\u8cc7\u6599\u4e2d\u5fc3\u4f5c\u696d\u7cfb\u7d71 NVIDIA Base Command<\/a> \u8edf\u9ad4\u7684\u652f\u63f4\u4e0b\uff0c\u6210\u70ba\u4e00\u500b\u5b8c\u5168\u6700\u4f73\u5316\u7684\u5e73\u53f0\u3002<\/p>\n\n\n\n

\u6bcf\u500b DGX H100 \u7cfb\u7d71\u642d\u8f09\u516b\u500b NVIDIA H100 GPU\u3001\u5341\u5f35 NVIDIA ConnectX-7<\/a> \u4e59\u592a\u7db2\u8def\u4ecb\u9762\u5361\u53ca\u5169\u500b\u7b2c\u56db\u4ee3 Intel Xeon \u53ef\u64f4\u5145\u8655\u7406\u5668\uff0c\u53ef\u63d0\u4f9b\u6253\u9020\u5927\u578b\u751f\u6210\u5f0f AI \u6a21\u578b\u3001\u5927\u578b\u8a9e\u8a00\u6a21\u578b<\/a>\u3001\u63a8\u85a6\u7cfb\u7d71<\/a>\u7b49\u6240\u9700\u7684\u6548\u80fd\u3002<\/p>\n\n\n\n

\u9019\u500b\u67b6\u69cb\u52a0\u4e0a NVIDIA \u7db2\u8def\u6280\u8853\uff0c\u80fd\u5920\u5927\u898f\u6a21\u63d0\u5347\u904b\u7b97\u6548\u7387\uff0c\u5728\u8a13\u7df4 AI \u53ca\u8655\u7406\u9ad8\u6548\u80fd\u904b\u7b97(HPC) \u4f5c\u696d\u8ca0\u8f09\u65b9\u9762\uff0c\u5176\u6548\u80fd\u8f03\u524d\u4e00\u4ee3\u7522\u54c1\u9ad8\u51fa 9 \u500d\uff0c\u6bd4\u672a\u52a0\u901f\u7684 X86 \u96d9\u63d2\u69fd\u4f3a\u670d\u5668\u9ad8\u51fa 20 \u81f3 40 \u500d\u3002\u8981\u662f\u904e\u53bb\u5728\u55ae\u7d14 X86 \u67b6\u69cb\u4f3a\u670d\u5668\u53e2\u96c6\u4e0a\u8a13\u7df4\u4e00\u500b\u8a9e\u8a00\u6a21\u578b\u8981 40 \u5929\u7684\u6642\u9593\uff0c\u5728\u642d\u8f09 Intel Xeon CPU \u53ca ConnectX-7 \u7db2\u8def\u6280\u8853\u7684 NVIDIA DGX H100 \u4e0a\u8a13\u7df4\u540c\u4e00\u500b\u8a9e\u8a00\u6a21\u578b\uff0c\u53ea\u8981\u77ed\u77ed\u7684\u4e00\u5230\u5169\u5929\u4fbf\u53ef\u5b8c\u6210\u3002<\/p>\n\n\n\n

NVIDIA DGX H100\u00a0\u7cfb\u7d71\u662f\u9069\u7528\u65bc\u4f01\u696d\u7684\u4e00\u7ad9\u5f0f\u00a0NVIDIA DGX SuperPOD<\/a>\u00a0\u7684\u69cb\u6210\u55ae\u5143\uff0c\u5176\u63d0\u4f9b\u9ad8\u9054\u00a01 exaflop<\/a>\u00a0\u7684\u00a0AI\u00a0\u904b\u7b97\u6548\u80fd\uff0c\u986f\u8457\u63d0\u5347\u5927\u898f\u6a21\u90e8\u7f72\u4f01\u696d\u00a0AI\u00a0\u7684\u6548\u7387\u3002<\/p>\n\n\n\n

<\/p>\n\n\n\n

NVIDIA <\/strong>\u5408\u4f5c\u5925\u4f34\u63d0\u5347\u8cc7\u6599\u4e2d\u5fc3\u7684\u904b\u4f5c\u6548\u7387<\/strong><\/strong><\/h3>\n\n\n\n

\u5c0d\u65bc\u8655\u7406 AI \u8cc7\u6599\u4e2d\u5fc3\u7684\u4f5c\u696d\u8ca0\u8f09\uff0cNVIDIA H100 GPU \u8b93\u4f01\u696d\u80fd\u5920\u66f4\u9ad8\u6548\u5730\u6253\u9020\u53ca\u90e8\u7f72\u61c9\u7528\u7a0b\u5f0f\u3002<\/p>\n\n\n\n

\u83ef\u78a9 (ASUS)\u3001\u6e90\u8a0a\u79d1\u6280 (Atos)\u3001\u601d\u79d1 (Cisco)\u3001\u6234\u723e\u79d1\u6280 (Dell Technologies)\u3001\u5bcc\u58eb\u901a (Fujitsu)\u3001\u6280\u5609 (GIGABYTE)\u3001\u6167\u8207\u79d1\u6280 (Hewlett Packard Enterprise)\u3001\u806f\u60f3 (Lenovo)\u3001\u96f2\u9054\u79d1\u6280 (QCT) \u53ca\u7f8e\u8d85\u5fae (Supermicro) \u7b49 NVIDIA \u7684\u5408\u4f5c\u5925\u4f34\uff0c\u5373\u5c07\u63a8\u51fa\u642d\u8f09 H100 GPU \u548c\u7b2c\u56db\u4ee3 Intel Xeon \u53ef\u64f4\u5145 CPU \u7684\u591a\u6b3e\u7cfb\u7d71\u7d44\u5408\uff0c\u5c07\u70ba\u5168\u7403\u4f01\u696d\u5e36\u4f86\u65b0\u4e00\u4ee3\u7684\u57f7\u884c\u6548\u80fd\u548c\u80fd\u6e90\u4f7f\u7528\u6548\u7387\u3002<\/p>\n\n\n\n

\u4f5c\u70ba\u672a\u4f86\u6548\u7387\u63d0\u5347\u7684\u9818\u982d\u7f8a\uff0cFlatiron Institute \u642d\u8f09 NVIDIA H100 GPU \u7684 Lenovo ThinkSystem \u8d85\u7d1a\u96fb\u8166<\/a>\uff0c\u69ae\u767b Green500 \u699c\u55ae\u6700\u7bc0\u80fd\u96fb\u8166\u4e4b\u51a0\uff0c\u800c\u5728\u699c\u55ae\u7684\u524d\u4e09\u5341\u540d\u8d85\u7d1a\u96fb\u8166\u7cfb\u7d71\u88e1\uff0c\u6709 23 \u5957\u7cfb\u7d71\u63a1\u7528 NVIDIA \u7684\u6280\u8853\u3002Flatiron \u7684\u8d85\u7d1a\u96fb\u8166\u7cfb\u7d71\u4f7f\u7528\u7684\u662f Intel \u7684\u524d\u4e00\u4ee3 CPU \u7522\u54c1\uff0c\u9810\u8a08\u76ee\u524d\u5373\u5c07\u4e0a\u5e02\u7684\u7cfb\u7d71\u6703\u5e36\u4f86\u66f4\u9ad8\u7684\u6548\u7387\u3002<\/p>\n\n\n\n

\u6b64\u5916\uff0c\u7528 NVIDIA ConnectX-7 \u7db2\u8def\u6280\u8853\u53ca Intel \u7b2c\u56db\u4ee3 Xeon \u53ef\u64f4\u5145\u8655\u7406\u5668\u9023\u63a5\u4f3a\u670d\u5668\uff0c\u5c07\u63d0\u9ad8\u4f3a\u670d\u5668\u7684\u904b\u4f5c\u6548\u7387\u3001\u6e1b\u5c11\u57fa\u790e\u8a2d\u65bd\u7684\u6578\u91cf\u53ca\u8017\u96fb\u91cf\u3002<\/p>\n\n\n\n

NVIDIA ConnectX-7\u00a0\u4e59\u592a\u7db2\u8def\u4ecb\u9762\u5361\u652f\u63f4\u00a0PCIe Gen 5\u00a0\u53ca\u6bcf\u79d2\u00a0400 GB\u00a0\u7684\u00a0InfiniBand\u00a0\u548c\u4e59\u592a\u7db2\u8def\u9023\u7dda\uff0c\u5c07\u4f3a\u670d\u5668\u4e4b\u9593\u53ca\u81f3\u5132\u5b58\u88dd\u7f6e\u7684\u7db2\u8def\u8f38\u9001\u91cf\u589e\u52a0\u4e00\u500d\u3002\u9019\u4e9b\u4e59\u592a\u7db2\u8def\u4ecb\u9762\u5361\u652f\u63f4\u5148\u9032\u7684\u7db2\u8def\u3001\u5132\u5b58\u88dd\u7f6e\u548c\u5b89\u5168\u5378\u8f09\u3002ConnectX-7\u00a0\u7db2\u8def\u6280\u8853\u6e1b\u5c11\u4e86\u6240\u9700\u7684\u96fb\u7dda\u548c\u4ea4\u63db\u6a5f\u9023\u63a5\u57e0\u7684\u6578\u91cf\uff0c\u70ba\u5927\u578b\u00a0GPU\u00a0\u52a0\u901f\u7684\u9ad8\u6548\u80fd\u904b\u7b97\u548c\u00a0AI\u00a0\u53e2\u96c6\u7684\u7db2\u8def\u7701\u4e0b\u00a017%\u00a0\u4ee5\u4e0a\u7684\u96fb\u529b\uff0c\u6709\u52a9\u65bc\u63d0\u9ad8\u9019\u4e9b\u65b0\u4f3a\u670d\u5668\u7684\u80fd\u6e90\u4f7f\u7528\u6548\u7387\u3002<\/p>\n\n\n\n

<\/p>\n\n\n\n

NVIDIA AI Enterprise <\/strong>\u8edf\u9ad4\u63d0\u4f9b\u5b8c\u6574\u5806\u758a\u7684<\/strong> AI <\/strong>\u89e3\u6c7a\u65b9\u6848<\/strong><\/strong><\/h3>\n\n\n\n

\u9019\u4e9b\u4e0b\u4e00\u4ee3\u7cfb\u7d71\u9084\u70ba NVIDIA AI Enterprise \u8edf\u9ad4\u5957\u4ef6<\/a>\u9032\u884c\u6700\u4f73\u5316\u8abf\u6574\uff0c\u5927\u5e45\u63d0\u5347\u904b\u4f5c\u6548\u7387\u3002<\/p>\n\n\n\n

\u5728 NVIDIA H100 \u4e0a\u904b\u884c\u7684 NVIDIA AI Enterprise \u52a0\u5feb\u63a8\u52d5\u8cc7\u6599\u79d1\u5b78\u5de5\u4f5c\u6d41\uff0c\u4ea6\u8b93\u958b\u767c\u548c\u90e8\u7f72\u9810\u6e2c\u6027 AI \u6a21\u578b\u7684\u4f5c\u696d\u8b8a\u5f97\u66f4\u7c21\u55ae\uff0c\u81ea\u52d5\u57f7\u884c\u57fa\u672c\u6d41\u7a0b\u53c8\u5feb\u901f\u5f9e\u8cc7\u6599\u88e1\u7372\u5f97\u6d1e\u5bdf\u3002<\/p>\n\n\n\n

\u6709\u8457\u5b8c\u6574\u5806\u758a\u8edf\u9ad4\u5eab\u7684 NVIDIA AI Enterprise\uff0c\u5176\u4e2d\u5305\u62ec\u53c3\u8003\u61c9\u7528\u7a0b\u5f0f\u3001\u6846\u67b6\u3001\u9810\u5148\u8a13\u7df4\u597d\u7684\u6a21\u578b\u53ca\u57fa\u790e\u8a2d\u65bd\u6700\u4f73\u5316\u7684 AI \u5de5\u4f5c\u6d41\u7a0b\uff0c\u662f\u9806\u5229\u64f4\u5927\u4f01\u696d AI\u7684\u4e00\u500b\u7406\u60f3\u57fa\u790e\u3002<\/p>\n\n\n\n

\u6b61\u8fce\u514d\u8cbb\u8a3b\u518a NVIDIA LaunchPad<\/a>\uff0c\u9ad4\u9a57\u5728 NVIDIA H100 \u4e0a\u57f7\u884c\u7531 NVIDIA AI Enterprise \u652f\u63f4\u7684 AI \u5de5\u4f5c\u6d41\u7a0b\u548c\u6846\u67b6\u3002<\/p>\n\n\n\n

\u656c\u8acb\u89c0\u770b\u00a0NVIDIA\u00a0\u5275\u8fa6\u4eba\u66a8\u57f7\u884c\u9577\u9ec3\u4ec1\u52f3<\/a>\u5728\u7b2c\u56db\u4ee3\u00a0Intel Xeon\u00a0\u53ef\u64f4\u5145\u8655\u7406\u4e0a\u5e02\u767c\u8868\u6703\u7684\u7cbe\u5f69\u6f14\u8b1b\u5167\u5bb9\u3002<\/p>\n\n\n\n

<\/p>\n\n\n\n

<\/p>\n\n\n\n

\ud83d\udfe6\u73fe\u5728\u5c31\u52a0\u5165 ioioTIMES \u81c9\u66f8\u7c89\u7d72\u5718<\/a> \u66f4\u591a\u4e92\u52d5\u3001\u66f4\u591a\u597d\u5eb7\u650f\u62b5\u52a0!!<\/strong>
\"\ud83d\udfe9\"\u6211\u5011\u6709LINE TODAY<\/a>\u983b\u9053\u4e86\uff0c\u5feb\u4f86\u8ffd\u8e2a\u6211\u5011\u5427!!–\u6700\u65b0\u79d1\u6280\u65b0\u805e \u76e1\u5728\u4f60\u624b<\/strong><\/h4>\n\n\n\n

<\/p>\n","protected":false},"excerpt":{"rendered":"

\u642d\u914d\u7b2c\u56db\u4ee3\u00a0Intel Xeon\u00a0\u53ef<\/p>\n","protected":false},"author":3,"featured_media":18905,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"rank_math_lock_modified_date":false,"footnotes":""},"categories":[13],"tags":[34,71,4292],"class_list":["post-18916","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-news","tag-intel","tag-nvidia","tag-4292"],"_links":{"self":[{"href":"https:\/\/www.ioiotimes.com\/index.php?rest_route=\/wp\/v2\/posts\/18916"}],"collection":[{"href":"https:\/\/www.ioiotimes.com\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.ioiotimes.com\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.ioiotimes.com\/index.php?rest_route=\/wp\/v2\/users\/3"}],"replies":[{"embeddable":true,"href":"https:\/\/www.ioiotimes.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=18916"}],"version-history":[{"count":1,"href":"https:\/\/www.ioiotimes.com\/index.php?rest_route=\/wp\/v2\/posts\/18916\/revisions"}],"predecessor-version":[{"id":18917,"href":"https:\/\/www.ioiotimes.com\/index.php?rest_route=\/wp\/v2\/posts\/18916\/revisions\/18917"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.ioiotimes.com\/index.php?rest_route=\/wp\/v2\/media\/18905"}],"wp:attachment":[{"href":"https:\/\/www.ioiotimes.com\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=18916"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.ioiotimes.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=18916"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.ioiotimes.com\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=18916"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}