{"id":125671,"date":"2025-10-14T18:48:00","date_gmt":"2025-10-14T10:48:00","guid":{"rendered":"https:\/\/www.ioiotimes.com\/?p=125671"},"modified":"2025-10-14T19:27:25","modified_gmt":"2025-10-14T11:27:25","slug":"nvidia%e8%88%87%e5%a4%a5%e4%bc%b4%e6%8e%a8%e5%8b%95%e7%82%bavera-rubin%e5%bb%ba%e8%a8%ad%e7%9a%84%e6%96%b0%e4%b8%96%e4%bb%a3%e3%80%81%e9%ab%98%e6%95%88%e7%8e%87%e7%99%be%e8%90%ac%e7%93%a9%e7%b4%9aai","status":"publish","type":"post","link":"https:\/\/www.ioiotimes.com\/?p=125671","title":{"rendered":"NVIDIA\u8207\u5925\u4f34\u63a8\u52d5\u70baVera Rubin\u5efa\u8a2d\u7684\u65b0\u4e16\u4ee3\u3001\u9ad8\u6548\u7387\u767e\u842c\u74e9\u7d1aAI\u5de5\u5ee0"},"content":{"rendered":"\n<p><strong>\u8d85\u904e50\u5bb6NVIDIA MGX\u5925\u4f34\u6b63\u70baNVIDIA Vera Rubin NVL144\u505a\u597d\u6e96\u5099\uff1b\u903e20\u5bb6\u4f01\u696d\u5c07\u52a0\u5165NVIDIA\u65e5\u76ca\u64f4\u5927\u7684\u751f\u614b\u7cfb\uff0c\u652f\u63f4800\u4f0f\u7279\u76f4\u6d41\u96fb\uff08VDC\uff09\u8cc7\u6599\u4e2d\u5fc3\uff0c\u4ee5\u5be6\u73fe\u672a\u4f86\u7684\u767e\u842c\u74e9\u7d1aAI\u5de5\u5ee0<\/strong><\/p>\n\n\n<div class=\"wp-block-image\">\n<figure class=\"aligncenter size-full is-resized\"><img loading=\"lazy\" decoding=\"async\" width=\"680\" height=\"382\" src=\"https:\/\/www.ioiotimes.com\/wordpress\/wp-content\/uploads\/2025\/10\/20251014-nvidia06.jpg\" alt=\"\" class=\"wp-image-125677\" style=\"width:774px;height:auto\" title=\"\" srcset=\"https:\/\/www.ioiotimes.com\/wordpress\/wp-content\/uploads\/2025\/10\/20251014-nvidia06.jpg 680w, https:\/\/www.ioiotimes.com\/wordpress\/wp-content\/uploads\/2025\/10\/20251014-nvidia06-300x169.jpg 300w\" sizes=\"(max-width: 680px) 100vw, 680px\" \/><\/figure><\/div>\n\n\n<p><\/p>\n\n\n\n<p>\u5728\u958b\u653e\u904b\u7b97\u8a08\u756b\u5168\u7403\u5cf0\u6703\uff08OCP Global Summit\uff09\u4e0a\uff0cNVIDIA \u5e36\u4f86\u767e\u842c\u74e9\uff08GW\uff09\u7d1a\u4eba\u5de5\u667a\u6167\uff08AI\uff09\u5de5\u5ee0\u7684\u672a\u4f86\u4e00\u77a5\u3002<\/p>\n\n\n\n<p>NVIDIA \u5c07\u516c\u5e03 NVIDIA Vera Rubin NVL144 MGX \u4e16\u4ee3\u958b\u653e\u5f0f\u67b6\u69cb\u6a5f\u67b6\u4f3a\u670d\u5668\u7684\u898f\u683c\u3002\u8d85\u904e 50 \u5bb6 MGX \u5925\u4f34\u6b63\u70ba\u6b64\u6295\u5165\u6e96\u5099\u5de5\u4f5c\uff0c\u540c\u6642\u70ba NVIDIA Kyber \u63d0\u4f9b\u751f\u614b\u7cfb\u652f\u63f4\u3002NVIDIA Kyber \u53ef\u9023\u7d50 576 \u9846 Rubin Ultra GPU\uff0c\u4ee5\u56e0\u61c9\u8207\u65e5\u4ff1\u589e\u7684\u63a8\u8ad6\u9700\u6c42\u3002<\/p>\n\n\n\n<p>\u903e 20 \u5bb6\u7522\u696d\u5925\u4f34\u6b63\u5c55\u793a\u65b0\u4e00\u4ee3\u6676\u7247\u3001\u96f6\u7d44\u4ef6\u8207\u96fb\u6e90\u7cfb\u7d71\uff0c\u4ee5\u53ca\u5c0d\u767e\u842c\u74e9\u7d1a\u65b0\u4e16\u4ee3 800 \u4f0f\u7279\u76f4\u6d41\u96fb\uff08VDC\uff09\u8cc7\u6599\u4e2d\u5fc3\u7684\u652f\u6301\uff0c\u9019\u4e9b\u8cc7\u6599\u4e2d\u5fc3\u5c07\u652f\u63f4 NVIDIA Kyber \u6a5f\u67b6\u67b6\u69cb\u3002<\/p>\n\n\n\n<p>\u9d3b\u6d77\u79d1\u6280\u96c6\u5718\u516c\u5e03\u5176\u4f4d\u65bc\u53f0\u7063\u7684 800 VDC\u300140 \u5343\u74e9\uff08MW\uff09\u8cc7\u6599\u4e2d\u5fc3 Kaohsiung-1 \u7684\u7d30\u7bc0\u3002CoreWeave\u3001Lambda\u3001Nebius\u3001Oracle Cloud Infrastructure \u8207 Together AI \u7b49\u7522\u696d\u5148\u9a45\u4e5f\u5728\u8a2d\u8a08 800 \u4f0f\u7279\u8cc7\u6599\u4e2d\u5fc3\u3002\u6b64\u5916\uff0c<a href=\"https:\/\/www.vertiv.com\/en-us\/about\/news-and-insights\/corporate-news\/from-vision-to-readiness-vertiv-collaborates-with-nvidia-to-advance-800-vdc-platform-designs-to-power-the-next-generation-of-ai-factories\/\" target=\"_blank\" rel=\"noreferrer noopener\">Vertiv<\/a> \u767c\u8868\u7bc0\u7701\u7a7a\u9593\u3001\u964d\u4f4e\u6210\u672c\u4e14\u9ad8\u6548\u7bc0\u80fd\u7684 800 VDC MGX \u53c3\u8003\u67b6\u69cb\uff0c\u4e00\u5957\u5b8c\u6574\u7684\u4f9b\u96fb\u8207\u51b7\u537b\u57fa\u790e\u8a2d\u65bd\u67b6\u69cb\u3002<a href=\"https:\/\/www.hpe.com\/us\/en\/newsroom\/blog-post\/2025\/10\/ocp-global-summit-hpes-next-gen-ai-solutions-and-quantum-resistant-security-innovate-upon-open-source-standards-and-modular-computing-solutions.html\" target=\"_blank\" rel=\"noreferrer noopener\">HPE<\/a> \u5ba3\u5e03\u5176\u7522\u54c1\u5c07\u652f\u63f4 NVIDIA Kyber \u53ca <a href=\"https:\/\/blogs.nvidia.com.tw\/blog\/nvidia-introduces-spectrum-xgs-ethernet-to-connect-distributed-data-centers-into-giga-scale-ai-super-factories\/\" target=\"_blank\" rel=\"noreferrer noopener\">NVIDIA Spectrum-XGS \u4e59\u592a\u7db2\u8def<\/a>\u64f4\u5c55\u6280\u8853\uff0c\u8a72\u6280\u8853\u5c6c\u65bc <a href=\"https:\/\/www.nvidia.com\/zh-tw\/networking\/spectrumx\/\" target=\"_blank\" rel=\"noreferrer noopener\">Spectrum-X \u4e59\u592a\u7db2\u8def\u5e73\u53f0<\/a>\u7684\u4e00\u90e8\u5206\u3002<\/p>\n\n\n\n<p>\u7531\u50b3\u7d71\u7684 415 \u6216 480 \u4f0f\u7279\u4ea4\u6d41\u96fb\uff08VAC\uff09\u4e09\u76f8\u7cfb\u7d71\u8f49\u5411 800 VDC \u57fa\u790e\u8a2d\u65bd\uff0c\u53ef\u63d0\u9ad8\u8cc7\u6599\u4e2d\u5fc3\u7684\u53ef\u64f4\u5c55\u6027\u3001\u63d0\u5347\u80fd\u6e90\u6548\u7387\u3001\u6e1b\u5c11\u6750\u6599\u4f7f\u7528\u4e26\u589e\u52a0\u6548\u80fd\u3002\u96fb\u52d5\u8eca\u8207\u592a\u967d\u80fd\u7522\u696d\u5df2\u63a1\u7528 800 VDC \u57fa\u790e\u8a2d\u65bd\uff0c\u4ee5\u7372\u5f97\u985e\u4f3c\u6548\u76ca\u3002<\/p>\n\n\n\n<p>\u7531 Meta \u5275\u7acb\u7684\u958b\u653e\u904b\u7b97\u8a08\u756b\uff08Open Compute Project\uff0cOCP\uff09\uff0c\u662f\u4e00\u500b\u7531\u6578\u767e\u5bb6\u904b\u7b97\u8207\u7db2\u8def\u4f9b\u61c9\u5546\u7d44\u6210\u7684\u7522\u696d\u806f\u76df\uff0c\u66f4\u5c08\u6ce8\u65bc\u91cd\u65b0\u8a2d\u8a08\u786c\u9ad4\u6280\u8853\uff0c\u4ee5\u6709\u6548\u652f\u63f4\u65e5\u76ca\u589e\u9577\u7684\u904b\u7b97\u57fa\u790e\u8a2d\u65bd\u9700\u6c42\u3002<\/p>\n\n\n\n<p><\/p>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>Vera Rubin NVL144\uff1a\u70baAI\u5de5\u5ee0\u800c\u751f\u7684\u64f4\u5c55\u8a2d\u8a08<\/strong><\/h3>\n\n\n\n<p>Vera Rubin NVL144 MGX \u904b\u7b97\u6258\u76e4\uff08compute tray\uff09\u63a1\u7528\u7bc0\u80fd\u3001100% \u6db2\u51b7\u7684\u6a21\u7d44\u5316\u8a2d\u8a08\u3002\u5176\u4e2d\u592e\u7684\u5370\u5237\u96fb\u8def\u677f\u4e2d\u4ecb\u80cc\u677f\u53d6\u4ee3\u50b3\u7d71\u7dda\u7e9c\u9023\u63a5\uff0c\u5be6\u73fe\u66f4\u5feb\u7684\u7d44\u88dd\u8207\u7dad\u8b77\uff0c\u4e26\u914d\u5099\u6a21\u7d44\u5316\u64f4\u5145\u63d2\u69fd\uff0c\u4ee5\u652f\u63f4 NVIDIA ConnectX-9 800GB\/s \u7db2\u8def\u8207 NVIDIA Rubin CPX \u5927\u898f\u6a21\u60c5\u5883<a href=\"https:\/\/www.nvidia.com\/en-us\/glossary\/ai-inference\/\" target=\"_blank\" rel=\"noreferrer noopener\">\u63a8\u8ad6<\/a>\u3002<\/p>\n\n\n\n<p>NVIDIA Vera Rubin NVL144 \u5728\u52a0\u901f\u904b\u7b97\u67b6\u69cb\u8207 AI \u6548\u80fd\u4e0a\u5e36\u4f86\u91cd\u5927\u8e8d\u9032\uff0c\u5c08\u70ba\u9032\u968e\u63a8\u7406\u5f15\u64ce\u8207 AI \u4ee3\u7406\u9700\u6c42\u6253\u9020\u3002<\/p>\n\n\n\n<p>\u6b64\u8a2d\u8a08\u4ee5 MGX \u6a5f\u67b6\u67b6\u69cb\u70ba\u6838\u5fc3\uff0c\u4e26\u5c07\u7372\u5f97\u8d85\u904e 50 \u5bb6 MGX \u7cfb\u7d71\u8207\u96f6\u7d44\u4ef6\u5925\u4f34\u7684\u652f\u63f4\u3002NVIDIA \u8a08\u5283\u5c07\u5347\u7d1a\u7248\u6a5f\u67b6\u53ca\u904b\u7b97\u6258\u76e4\u5275\u65b0\u8ca2\u737b\u7d66 OCP \u806f\u76df\u4f5c\u70ba\u958b\u653e\u6a19\u6e96\u3002<\/p>\n\n\n\n<p>OCP \u806f\u76df\u7684\u904b\u7b97\u6258\u76e4\u8207\u6a5f\u67b6\u6a19\u6e96\uff0c\u8b93\u5925\u4f34\u80fd\u4ee5\u6a21\u7d44\u5316\u65b9\u5f0f\u81ea\u7531\u642d\u914d\uff0c\u4e26\u96a8\u67b6\u69cb\u64f4\u5c55\u800c\u66f4\u5feb\u5730\u64f4\u5c55\u3002Vera Rubin NVL144 \u6a5f\u67b6\u8a2d\u8a08\u63a1\u7528\u7bc0\u80fd\u7684 45\u00b0C \u6db2\u51b7\u7cfb\u7d71\uff0c\u914d\u5099\u65b0\u578b\u6db2\u51b7\u532f\u6d41\u6392\u63d0\u5347\u6548\u80fd\uff0c\u4e26\u589e\u52a0 20 \u500d\u7684\u5132\u80fd\u5bb9\u91cf\uff0c\u78ba\u4fdd\u4f9b\u96fb\u7a69\u5b9a\u3002<\/p>\n\n\n\n<p>MGX \u5c0d\u904b\u7b97\u6258\u76e4\u8207\u6a5f\u67b6\u67b6\u69cb\u7684\u5347\u7d1a\uff0c\u63d0\u5347 AI \u5de5\u5ee0\u6548\u80fd\uff0c\u540c\u6642\u7c21\u5316\u7d44\u88dd\u7a0b\u5e8f\uff0c\u5f9e\u800c\u80fd\u5920\u5feb\u901f\u5efa\u69cb\u767e\u842c\u74e9\u7d1a AI \u57fa\u790e\u8a2d\u65bd\u3002<\/p>\n\n\n\n<p>NVIDIA \u662f\u6a6b\u8de8\u591a\u4e16\u4ee3\u786c\u9ad4 OCP \u6a19\u6e96\u7684\u4e3b\u8981\u8ca2\u737b\u8005\uff0c\u5176\u4e2d\u5305\u542b NVIDIA GB200 NVL72 \u7cfb\u7d71<a href=\"https:\/\/blogs.nvidia.com.tw\/blog\/nvidia-contributes-blackwell-platform-design-to-open-hardware-ecosystem-accelerating-ai-infrastructure-innovation\/\" target=\"_blank\" rel=\"noreferrer noopener\">\u95dc\u9375\u7684\u6a5f\u96fb\u8a2d\u8a08\u90e8\u5206<\/a>\u3002\u76f8\u540c\u7684 MGX \u6a5f\u67b6\u898f\u683c\u4e0d\u50c5\u652f\u63f4 GB300 NVL72\uff0c\u672a\u4f86\u66f4\u5c07\u652f\u63f4 Vera Rubin NVL144\u3001Vera Rubin NVL144 CPX \u8207 Vera Rubin CPX\uff0c\u4ee5\u5be6\u73fe\u66f4\u9ad8\u6548\u80fd\u8207\u66f4\u5feb\u901f\u7684\u90e8\u7f72\u3002<\/p>\n\n\n\n<p><\/p>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>\u53ea\u8981\u5efa\u597d\uff0c\u773e\u4eba\u7686\u4f86\uff1aNVIDIA Kyber\u6a5f\u67b6\u4f3a\u670d\u5668\u4e16\u4ee3<\/strong><\/h3>\n\n\n\n<p>OCP \u751f\u614b\u7cfb\u4e5f\u6b63\u5728\u70ba NVIDIA Kyber \u505a\u6e96\u5099\uff0c\u5176\u5275\u65b0\u4e4b\u8655\u5728\u65bc\u5c0e\u5165 800 VDC \u4f9b\u96fb\u3001\u6db2\u51b7\u8207\u6a5f\u68b0\u8a2d\u8a08\u3002<\/p>\n\n\n\n<p>\u9019\u4e9b\u5275\u65b0\u5c07\u63a8\u52d5\u9081\u5411 NVIDIA Kyber \u6a5f\u67b6\u4f3a\u670d\u5668\u4e16\u4ee3\u7684\u8f49\u578b\u3002NVIDIA Kyber \u662f\u63a5\u66ff NVIDIA Oberon \u7684\u5e73\u53f0\uff0c\u9810\u8a08\u5728 2027 \u5e74\u642d\u8f09\u5bb9\u7d0d 576 \u9846 NVIDIA Rubin Ultra GPU \u7684\u9ad8\u5bc6\u5ea6\u5e73\u53f0\u3002<\/p>\n\n\n\n<p>\u61c9\u5c0d\u9ad8\u529f\u7387\u914d\u96fb\u6311\u6230\u6700\u6709\u6548\u7684\u65b9\u5f0f\u662f\u63d0\u9ad8\u96fb\u58d3\u3002\u7531\u50b3\u7d71\u7684 415 \u6216 480 VAC \u4e09\u76f8\u7cfb\u7d71\u904e\u6e21\u5230 800 VDC \u67b6\u69cb\u53ef\u5e36\u4f86\u591a\u91cd\u6548\u76ca\u3002<\/p>\n\n\n\n<p>\u9019\u9805\u8f49\u578b\u8b93\u6a5f\u67b6\u4f3a\u670d\u5668\u5925\u4f34\u5f97\u4ee5\u628a\u6a5f\u67b6\u5167\u90e8\u7684 54 VDC \u5143\u4ef6\u5347\u7d1a\u81f3 800 VDC\uff0c\u4ee5\u7372\u5f97\u66f4\u4f73\u6210\u679c\u3002\u7531\u76f4\u6d41\u96fb\u57fa\u790e\u8a2d\u65bd\u4f9b\u61c9\u5546\u3001\u96fb\u6e90\u7cfb\u7d71\u8207\u51b7\u537b\u5925\u4f34\uff0c\u4ee5\u53ca\u6676\u7247\u88fd\u9020\u5546\u6240\u7d44\u6210\u7684\u751f\u614b\u7cfb\u9f4a\u805a\u672c\u6b21 OCP \u5168\u7403\u5cf0\u6703\uff0c\u6240\u6709\u53c3\u8207\u8005\u7686\u4f9d\u5faa MGX \u6a5f\u67b6\u4f3a\u670d\u5668\u53c3\u8003\u67b6\u69cb\u7684\u958b\u653e\u6a19\u6e96\u3002<\/p>\n\n\n\n<p>NVIDIA Kyber \u5c08\u70ba\u63d0\u5347\u6a5f\u67b6\u5167 GPU \u5bc6\u5ea6\u3001\u64f4\u5c55\u7db2\u8def\u898f\u6a21\uff0c\u4e26\u5c07\u5927\u578b AI \u57fa\u790e\u8a2d\u65bd\u7684\u6548\u80fd\u6975\u5927\u5316\u800c\u8a2d\u8a08\u3002\u900f\u904e\u5c07\u904b\u7b97\u5200\u92d2\uff08compute blade\uff09\u5982\u540c\u66f8\u67b6\u4e0a\u7684\u66f8\u672c\u822c\u5782\u76f4\u65cb\u8f49\u6392\u5217\uff0cKyber \u6bcf\u90e8\u6a5f\u7bb1\u6700\u591a\u53ef\u5bb9\u7d0d 18 \u7d44\u904b\u7b97\u5200\u92d2\uff0c\u540c\u6642\u900f\u904e\u7121\u7dda\u4e2d\u4ecb\u80cc\u677f\u5728\u6a5f\u7bb1\u5f8c\u65b9\u6574\u5408\u5c08\u7528\u7684 <a href=\"https:\/\/www.nvidia.com\/zh-tw\/data-center\/nvlink\/\" target=\"_blank\" rel=\"noreferrer noopener\">NVIDIA NVLink<\/a> \u4ea4\u63db\u5200\u92d2\uff0c\u5be6\u73fe\u7121\u7e2b\u7684\u64f4\u5c55\u7db2\u8def\u3002<\/p>\n\n\n\n<p>\u4f7f\u7528 800 VDC \u5f8c\uff0c\u76f8\u540c\u9285\u7dda\u53ef\u50b3\u8f38 150% \u4ee5\u4e0a\u7684\u96fb\u6e90\uff0c\u7121\u9700\u518d\u4ee5 200 \u516c\u65a4\u91cd\u7684\u9285\u6bcd\u7dda\u4f86\u70ba\u55ae\u4e00\u6a5f\u67b6\u4f9b\u96fb\u3002<\/p>\n\n\n\n<p>Kyber \u5c07\u6210\u70ba\u8d85\u5927\u898f\u6a21 AI \u8cc7\u6599\u4e2d\u5fc3\u7684\u57fa\u790e\u5143\u7d20\uff0c\u5728\u672a\u4f86\u5e7e\u5e74\u70ba\u6700\u5148\u9032\u7684\u751f\u6210\u5f0f AI \u5de5\u4f5c\u8ca0\u8f09\u5e36\u4f86\u5353\u8d8a\u6548\u80fd\u3001\u6548\u7387\u8207\u53ef\u9760\u6027\u3002NVIDIA Kyber \u6a5f\u67b6\u53ef\u5354\u52a9\u5ba2\u6236\u6e1b\u5c11\u6578\u5678\u7d1a\u9285\u6750\u7528\u91cf\uff0c\u9032\u800c\u7bc0\u7701\u6578\u767e\u842c\u7f8e\u5143\u7684\u6210\u672c\u3002<\/p>\n\n\n\n<p><\/p>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>NVIDIA NVLink Fusion\u751f\u614b\u7cfb\u64f4\u5927<\/strong><\/h3>\n\n\n\n<p>\u9664\u4e86\u786c\u9ad4\u5c64\u9762\uff0cNVIDIA NVLink Fusion \u6b63\u52a0\u901f\u767c\u5c55\uff0c\u5354\u52a9\u4f01\u696d\u628a\u5176\u534a\u5ba2\u88fd\u5316\u6676\u7247\u7121\u7e2b\u6574\u5408\u81f3\u9ad8\u5ea6\u6700\u4f73\u5316\u4e14\u5ee3\u6cdb\u90e8\u7f72\u7684\u8cc7\u6599\u4e2d\u5fc3\u67b6\u69cb\uff0c\u5f9e\u800c\u964d\u4f4e\u8907\u96dc\u5ea6\u4e26\u52a0\u901f\u4e0a\u5e02\u6642\u7a0b\u3002<\/p>\n\n\n\n<p>Intel \u8207 Samsung Foundry \u52a0\u5165 NVLink Fusion \u751f\u614b\u7cfb\uff0c\u8a72\u751f\u614b\u7cfb\u6db5\u84cb\u5ba2\u88fd\u5316\u6676\u7247\u8a2d\u8a08\u5546\u3001CPU \u8207 IP \u5925\u4f34\uff0c\u5354\u52a9 AI \u5de5\u5ee0\u5feb\u901f\u64f4\u5c55\uff0c\u4ee5\u8655\u7406\u6a21\u578b\u8a13\u7df4\u8207\u4ee3\u7406\u578b AI \u63a8\u8ad6\u7b49\u9ad8\u5f37\u5ea6\u5de5\u4f5c\u8ca0\u8f09\u3002<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li>\u3000\u25cf\u3000\u4f9d\u64da\u8fd1\u671f\u5ba3\u5e03\u7684 <a href=\"https:\/\/blogs.nvidia.com.tw\/blog\/nvidia-and-intel-to-develop-ai-infrastructure-and-personal-computing-products\/\" target=\"_blank\" rel=\"noreferrer noopener\">NVIDIA \u8207 Intel \u5408\u4f5c\u8a08\u756b<\/a>\uff0cIntel \u5c07\u900f\u904e NVLink Fusion \u5efa\u69cb\u53ef\u6574\u5408\u81f3 NVIDIA \u57fa\u790e\u8a2d\u65bd\u5e73\u53f0\u7684 x86 CPU\u3002<\/li>\n\n\n\n<li>\u3000\u25cf\u3000Samsung Foundry \u8207 NVIDIA \u5408\u4f5c\uff0c\u4ee5\u6eff\u8db3\u65e5\u76ca\u589e\u9577\u7684\u5ba2\u88fd\u5316 CPU \u8207\u5ba2\u88fd\u5316 XPU \u7684\u9700\u6c42\uff0c\u70ba\u5ba2\u88fd\u5316\u6676\u7247\u63d0\u4f9b\u5f9e\u8a2d\u8a08\u5230\u88fd\u9020\u7684\u5168\u6d41\u7a0b\u7d93\u9a57\u3002<\/li>\n<\/ul>\n\n\n\n<p><\/p>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>\u958b\u653e\u751f\u614b\u7cfb\u4e0d\u53ef\u6216\u7f3a\uff1a\u64f4\u5c55\u4e0b\u4e00\u4ee3AI\u5de5\u5ee0<\/strong><\/h3>\n\n\n\n<p>\u8d85\u904e 20 \u5bb6 NVIDIA \u5925\u4f34\u6b63\u5354\u529b\u63d0\u4f9b\u63a1\u7528\u958b\u653e\u6a19\u6e96\u7684\u6a5f\u67b6\u4f3a\u670d\u5668\uff0c\u4fc3\u6210\u672a\u4f86\u7684\u767e\u842c\u74e9\u7d1a AI \u5de5\u5ee0\u3002<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li>\u3000\u25cf\u3000<strong>\u6676\u7247\u4f9b\u61c9\u5546\uff1a<\/strong>Analog Devices, Inc.\uff08ADI\uff09\u3001<a href=\"https:\/\/www.aosmd.com\/news\/alpha-and-omega-semiconductor-supports-800-vdc-power-architecture-next-generation-ai-factories\" target=\"_blank\" rel=\"noreferrer noopener\">AOS<\/a>\u3001<a href=\"https:\/\/epc-co.com\/epc\/about-epc\/events-and-news\/news\/artmid\/1627\/articleid\/3241\/epc-800-vdc-power-architecture-for-ai-data-centers\" target=\"_blank\" rel=\"noreferrer noopener\">EPC<\/a>\u3001Infineon\u3001<a href=\"https:\/\/www.innoscience.com\/site\/details\/1024?el=mdnav\" target=\"_blank\" rel=\"noreferrer noopener\">Innoscience<\/a>\u3001MPS\u3001Navitas\u3001onsemi\u3001<a href=\"https:\/\/investors.power.com\/news\/news-details\/2025\/Power-Integrations-Details-1250-V-and-1700-V-PowiGaN-Technology-for-Next-Generation-800-VDC-AI-Data-Centers\/default.aspx?language=en&amp;_gl=1*jn18n6*_ga*MTQ0MjQwMDI3Mi4xNzM3NTU5Nzg0*_ga_2CDVGJMVN5*czE3NjAzNzQ4NzAkbzgwJGcwJHQxNzYwMzc0ODcwJGo2MCRsMCRoMA..\" target=\"_blank\" rel=\"noreferrer noopener\">Power Integrations<\/a>\u3001<a href=\"https:\/\/www.renesas.com\/en\/node\/25577451\" target=\"_blank\" rel=\"noreferrer noopener\">Renesas<\/a>\u3001\u7acb\u9321\u79d1\u6280\u3001<a href=\"https:\/\/www.rohm.com\/news-detail?news-title=2025-10-14_news_white-paper&amp;defaultGroupId=false\" target=\"_blank\" rel=\"noreferrer noopener\">ROHM<\/a>\u3001<a href=\"https:\/\/newsroom.st.com\/media-center\/press-item.html\/t4727.html\" target=\"_blank\" rel=\"noreferrer noopener\">STMicroelectronics<\/a>\u3001<a href=\"https:\/\/www.ti.com\/about-ti\/newsroom\/news-releases\/2025\/tis-new-power-management-solutions-enable-scalable-ai-infrastructures.html\" target=\"_blank\" rel=\"noreferrer noopener\">Texas Instruments<\/a>\u3002<\/li>\n\n\n\n<li>\u3000\u25cf\u3000<strong>\u96fb\u6e90\u7cfb\u7d71\u96f6\u7d44\u4ef6\u4f9b\u61c9\u5546\uff1a<\/strong><a href=\"https:\/\/www.bizlinktech.com\/news\/bizlink-showcasing-complete-ai-and-hpc-rack-solutions-at-ocp-global-summit-2025\/\" target=\"_blank\" rel=\"noreferrer noopener\">BizLink<\/a>\u3001\u53f0\u9054\u3001<a href=\"https:\/\/flex.com\/resources\/advancing-the-transition-to-800-vdc-data-centers-with-nvidia\" target=\"_blank\" rel=\"noreferrer noopener\">Flex<\/a>\u3001GE Vernova\u3001Lead Wealth\u3001\u5149\u5bf6\u79d1\u6280\u3001Megmeet\u3002<\/li>\n\n\n\n<li>\u3000\u25cf\u3000<strong>\u8cc7\u6599\u4e2d\u5fc3\u96fb\u6e90\u7cfb\u7d71\u4f9b\u61c9\u5546\uff1a<\/strong><a href=\"https:\/\/new.abb.com\/news\/detail\/129805\/abb-to-develop-next-generation-ai-data-centers-with-nvidia\" target=\"_blank\" rel=\"noreferrer noopener\">ABB<\/a>\u3001<a href=\"https:\/\/www.eaton.com\/us\/en-us\/company\/news-insights\/news-releases\/2025\/eaton-unveils-next-generation-architecture.html\" target=\"_blank\" rel=\"noreferrer noopener\">Eaton<\/a>\u3001GE Vernova\u3001<a href=\"https:\/\/heronpower.com\/\" target=\"_blank\" rel=\"noreferrer noopener\">Heron Power<\/a>\u3001<a href=\"https:\/\/www.hitachienergy.com\/news-and-events\/press-releases\/2025\/10\/nvidia-800-vdc-collaboration\" target=\"_blank\" rel=\"noreferrer noopener\">Hitachi Energy<\/a>\u3001<a href=\"https:\/\/www.businesswire.com\/news\/home\/20251013882999\/en\/Mitsubishi-Electric-to-Power-Next-Generation-AI-Factories-with-800-VDC-Infrastructure\" target=\"_blank\" rel=\"noreferrer noopener\">Mitsubishi Electric<\/a>\u3001Schneider Electric\u3001Siemens\u3001<a href=\"https:\/\/www.vertiv.com\/en-us\/about\/news-and-insights\/corporate-news\/from-vision-to-readiness-vertiv-collaborates-with-nvidia-to-advance-800-vdc-platform-designs-to-power-the-next-generation-of-ai-factories\/\" target=\"_blank\" rel=\"noreferrer noopener\">Vertiv<\/a>\u3002<\/li>\n<\/ul>\n\n\n\n<p><\/p>\n\n\n\n<p><em>\u6b32\u4e86\u89e3\u95dc\u65bc NVIDIA \u8207<\/em><a href=\"https:\/\/www.nvidia.com\/en-us\/events\/ocp-summit\/\" target=\"_blank\" rel=\"noreferrer noopener\"><em>\u958b\u653e\u904b\u7b97\u8a08\u756b\uff08Open Compute Project\uff09<\/em><\/a><em>\u7684\u66f4\u591a\u8cc7\u8a0a\uff0c\u6b61\u8fce\u53c3\u8207 10 \u6708 13 \u65e5\u81f3 16 \u65e5\u65bc\u8056\u8377\u897f\u6703\u8b70\u4e2d\u5fc3\u8209\u884c\u7684 OCP Global Summit\u3002<\/em><\/p>\n\n\n\n<p><\/p>\n\n\n\n<p>\u3000\u3000\u3000\u3000<\/p>\n\n\n\n<h4 class=\"wp-block-heading has-text-align-right has-very-light-gray-to-cyan-bluish-gray-gradient-background has-background\">\ud83d\udfe6<a href=\"https:\/\/reurl.cc\/lYKQaY\" data-type=\"link\" data-id=\"https:\/\/reurl.cc\/lYKQaY\" target=\"_blank\" rel=\"noopener\">\u770b\u6587\u7ae0\u5f97Mercusys Wi-Fi 7\u8def\u7531\u5668 <\/a><br>\ud83d\udfe6\u73fe\u5728\u5c31\u52a0\u5165&nbsp;ioioTIMES \u81c9\u66f8\u7c89\u7d72\u5718&nbsp;\u66f4\u591a\u4e92\u52d5\u3001\u66f4\u591a\u597d\u5eb7\u650f\u62b5\u52a0!!<br>\ud83d\udfe6<strong>\u6211\u5011\u6709<a href=\"https:\/\/today.line.me\/tw\/v2\/publisher\/103117\" target=\"_blank\" rel=\"noreferrer noopener nofollow\">LINE TODAY<\/a>\u983b\u9053\u4e86\uff0c\u5feb\u4f86\u8ffd\u8e2a\u6211\u5011\u5427!!&#8211;\u6700\u65b0\u79d1\u6280\u65b0\u805e \u76e1\u5728\u4f60<\/strong>\u624b<br><\/h4>\n","protected":false},"excerpt":{"rendered":"<p>\u8d85\u904e50\u5bb6NVIDIA MGX\u5925\u4f34\u6b63<\/p>\n","protected":false},"author":3,"featured_media":125677,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"rank_math_lock_modified_date":false,"footnotes":""},"categories":[13],"tags":[11604,15502,71,13740,15501],"class_list":["post-125671","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-news","tag-ai","tag-mgx","tag-nvidia","tag-vera-rubin","tag-15501"],"_links":{"self":[{"href":"https:\/\/www.ioiotimes.com\/index.php?rest_route=\/wp\/v2\/posts\/125671"}],"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=125671"}],"version-history":[{"count":2,"href":"https:\/\/www.ioiotimes.com\/index.php?rest_route=\/wp\/v2\/posts\/125671\/revisions"}],"predecessor-version":[{"id":125686,"href":"https:\/\/www.ioiotimes.com\/index.php?rest_route=\/wp\/v2\/posts\/125671\/revisions\/125686"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.ioiotimes.com\/index.php?rest_route=\/wp\/v2\/media\/125677"}],"wp:attachment":[{"href":"https:\/\/www.ioiotimes.com\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=125671"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.ioiotimes.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=125671"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.ioiotimes.com\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=125671"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}