{"id":85146,"date":"2025-03-19T18:00:07","date_gmt":"2025-03-20T01:00:07","guid":{"rendered":"https:\/\/phisonblog.com\/?p=85146"},"modified":"2025-04-14T10:07:50","modified_gmt":"2025-04-14T17:07:50","slug":"phison-adlink-advances-edge-ai-and-gen-ai-innovations-at-nvidia-gtc-2025","status":"publish","type":"post","link":"https:\/\/phisonblog.com\/zh\/phison-adlink-advances-edge-ai-and-gen-ai-innovations-at-nvidia-gtc-2025\/","title":{"rendered":"\u7fa4\u8054\u7535\u5b50 \u2013 \u51cc\u534e\u79d1\u6280\u5728 NVIDIA GTC 2025 \u4e0a\u63a8\u8fdb\u8fb9\u7f18 AI \u548c Gen AI \u521b\u65b0"},"content":{"rendered":"<p>[et_pb_section fb_built=&#8221;1&#8243; _builder_version=&#8221;4.16&#8243; global_colors_info=&#8221;{}&#8221;][et_pb_row _builder_version=&#8221;4.16&#8243; background_size=&#8221;initial&#8221; background_position=&#8221;top_left&#8221; background_repeat=&#8221;repeat&#8221; global_colors_info=&#8221;{}&#8221;][et_pb_column type=&#8221;4_4&#8243; _builder_version=&#8221;4.16&#8243; custom_padding=&#8221;|||&#8221; global_colors_info=&#8221;{}&#8221; custom_padding__hover=&#8221;|||&#8221;][et_pb_text _builder_version=&#8221;4.16&#8243; background_size=&#8221;initial&#8221; background_position=&#8221;top_left&#8221; background_repeat=&#8221;repeat&#8221; global_colors_info=&#8221;{}&#8221;]&#8221;<strong class=\"mdc-article-strong\" data-v-43363f62=\"\" data-v-02ca9be7=\"\">Summary:<\/strong><\/p>\n<ul>\n<li>Breaking barriers in Generative AI, the\u00a0<span class=\"mdc-article-underline\" data-v-7ddb3a4c=\"\" data-v-6f730619=\"\"><a class=\"mdc-link mds-link mdc-link--body\" tabindex=\"0\" href=\"https:\/\/c212.net\/c\/link\/?t=0&amp;l=en&amp;o=4383186-1&amp;h=17195712&amp;u=https%3A%2F%2Fwww.adlinktech.com%2Fen%2Fdlap%3Futm_source%3Dwebsite%26utm_medium%3Dreferral%26utm_campaign%3Dpartner-nvidia-pr-gtc-2025&amp;a=DLAP+Super+and+Supreme+series\" data-v-4234e9e2=\"\" data-v-7ddb3a4c=\"\" target=\"_blank\" rel=\"noopener\">DLAP Super and Supreme series<\/a><\/span>\u00a0elevate Edge AI performance, unlocking next-level Edge AI with Phison aiDAPTIV+ and\u00a0<span class=\"mdc-article-underline\" data-v-7ddb3a4c=\"\" data-v-6f730619=\"\"><a class=\"mdc-link mds-link mdc-link--body\" tabindex=\"0\" href=\"https:\/\/c212.net\/c\/link\/?t=0&amp;l=en&amp;o=4383186-1&amp;h=588825158&amp;u=https%3A%2F%2Fwww.nvidia.com%2Fen-us%2Fautonomous-machines%2Fembedded-systems%2Fjetson-orin%2F&amp;a=NVIDIA\" data-v-4234e9e2=\"\" data-v-7ddb3a4c=\"\" target=\"_blank\" rel=\"noopener\">NVIDIA<\/a><a class=\"mdc-link mds-link mdc-link--body\" tabindex=\"0\" href=\"https:\/\/c212.net\/c\/link\/?t=0&amp;l=en&amp;o=4383186-1&amp;h=124852239&amp;u=https%3A%2F%2Fwww.nvidia.com%2Fen-us%2Fautonomous-machines%2Fembedded-systems%2Fjetson-orin%2F&amp;a=+Jetson+Orin\" data-v-4234e9e2=\"\" data-v-7ddb3a4c=\"\" target=\"_blank\" rel=\"noopener\">\u00a0Jetson Orin<\/a><\/span> Super Mode.<\/li>\n<\/ul>\n<p>. . .<\/p>\n<p><strong class=\"mdc-article-strong\" data-v-43363f62=\"\" data-v-02ca9be7=\"\">Accelerating Economical Generative AI at the Edge<br data-v-43363f62=\"\" \/><\/strong>Generative AI adoption at edge devices is often limited by DRAM capacity constraints when running large language models (LLM). The DLAP Supreme series, featuring NVIDIA Jetson AGX Orin, elevates AI power with Phison aiDAPTIV+ technology, effectively overcoming token length limitations and enhancing inference speed.\u00a0 For instance, using the DLAP-411 Orin Supreme equipped with an NVIDIA Jetson AGX Orin 64GB configuration alongside the Llama3.1-<span data-v-02ca9be7=\"\">70B<\/span> model, the inference TTFT is improved by 52 times, and token length increased by 4 times. The DLAP Super series, geared up with NVIDIA Jetson Orin Super Mode, offers a robust, software-optimized framework with AI TOPS increased by up to 1.7 times and GenAI model performance improved by up to 2 times. The DLAP Super and Supreme series aim to accelerate the deployment of generative AI applications at the edge.&#8221;- morningstar.com<\/p>\n<p>Source: <a href=\"https:\/\/www.morningstar.com\/news\/pr-newswire\/20250318ny41141\/adlink-advances-edge-ai-and-generative-ai-innovations-at-nvidia-gtc-2025\" target=\"_blank\" rel=\"noopener\">morningstar.com<\/a><br \/>\n[\/et_pb_text][\/et_pb_column][\/et_pb_row][\/et_pb_section]<\/p>\n","protected":false},"excerpt":{"rendered":"<p>&#8220;Summary: Breaking barriers in Generative AI, the\u00a0DLAP Super and Supreme series\u00a0elevate Edge AI performance, unlocking next-level Edge AI with Phison aiDAPTIV+ and\u00a0NVIDIA\u00a0Jetson Orin Super Mode. . . . Accelerating Economical Generative AI at the EdgeGenerative AI adoption at edge devices is often limited by DRAM capacity constraints when running large language models (LLM). The DLAP [&hellip;]<\/p>\n","protected":false},"author":10,"featured_media":85148,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"_et_pb_use_builder":"on","_et_pb_old_content":"<p>\"<strong class=\"mdc-article-strong\" data-v-43363f62=\"\" data-v-02ca9be7=\"\">Summary:<\/strong><\/p><ul><li>Breaking barriers in Generative AI, the\u00a0<span class=\"mdc-article-underline\" data-v-7ddb3a4c=\"\" data-v-6f730619=\"\"><a class=\"mdc-link mds-link mdc-link--body\" tabindex=\"0\" href=\"https:\/\/c212.net\/c\/link\/?t=0&l=en&o=4383186-1&h=17195712&u=https%3A%2F%2Fwww.adlinktech.com%2Fen%2Fdlap%3Futm_source%3Dwebsite%26utm_medium%3Dreferral%26utm_campaign%3Dpartner-nvidia-pr-gtc-2025&a=DLAP+Super+and+Supreme+series\" data-v-4234e9e2=\"\" data-v-7ddb3a4c=\"\">DLAP Super and Supreme series<\/a><\/span>\u00a0elevate Edge AI performance, unlocking next-level Edge AI with Phison aiDAPTIV+ and\u00a0<span class=\"mdc-article-underline\" data-v-7ddb3a4c=\"\" data-v-6f730619=\"\"><a class=\"mdc-link mds-link mdc-link--body\" tabindex=\"0\" href=\"https:\/\/c212.net\/c\/link\/?t=0&l=en&o=4383186-1&h=588825158&u=https%3A%2F%2Fwww.nvidia.com%2Fen-us%2Fautonomous-machines%2Fembedded-systems%2Fjetson-orin%2F&a=NVIDIA\" data-v-4234e9e2=\"\" data-v-7ddb3a4c=\"\">NVIDIA<\/a><a class=\"mdc-link mds-link mdc-link--body\" tabindex=\"0\" href=\"https:\/\/c212.net\/c\/link\/?t=0&l=en&o=4383186-1&h=124852239&u=https%3A%2F%2Fwww.nvidia.com%2Fen-us%2Fautonomous-machines%2Fembedded-systems%2Fjetson-orin%2F&a=+Jetson+Orin\" data-v-4234e9e2=\"\" data-v-7ddb3a4c=\"\">\u00a0Jetson Orin<\/a><\/span> Super Mode.<\/li><\/ul><p>. . .<\/p><p><strong class=\"mdc-article-strong\" data-v-43363f62=\"\" data-v-02ca9be7=\"\">Accelerating Economical Generative AI at the Edge<br data-v-43363f62=\"\" \/><\/strong>Generative AI adoption at edge devices is often limited by DRAM capacity constraints when running large language models (LLM). The DLAP Supreme series, featuring NVIDIA Jetson AGX Orin, elevates AI power with Phison aiDAPTIV+ technology, effectively overcoming token length limitations and enhancing inference speed.\u00a0 For instance, using the DLAP-411 Orin Supreme equipped with an NVIDIA Jetson AGX Orin 64GB configuration alongside the Llama3.1-<span data-v-02ca9be7=\"\">70B<\/span> model, the inference TTFT is improved by 52 times, and token length increased by 4 times. The DLAP Super series, geared up with NVIDIA Jetson Orin Super Mode, offers a robust, software-optimized framework with AI TOPS increased by up to 1.7 times and GenAI model performance improved by up to 2 times. The DLAP Super and Supreme series aim to accelerate the deployment of generative AI applications at the edge.\"- morningstar.com<\/p><p>Source: <a href=\"https:\/\/www.morningstar.com\/news\/pr-newswire\/20250318ny41141\/adlink-advances-edge-ai-and-generative-ai-innovations-at-nvidia-gtc-2025\">morningstar.com<\/a><\/p>","_et_gb_content_width":"","inline_featured_image":false,"footnotes":""},"categories":[114],"tags":[22],"class_list":["post-85146","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-phison-in-the-news","tag-long-content"],"acf":[],"_links":{"self":[{"href":"https:\/\/phisonblog.com\/zh\/wp-json\/wp\/v2\/posts\/85146","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/phisonblog.com\/zh\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/phisonblog.com\/zh\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/phisonblog.com\/zh\/wp-json\/wp\/v2\/users\/10"}],"replies":[{"embeddable":true,"href":"https:\/\/phisonblog.com\/zh\/wp-json\/wp\/v2\/comments?post=85146"}],"version-history":[{"count":4,"href":"https:\/\/phisonblog.com\/zh\/wp-json\/wp\/v2\/posts\/85146\/revisions"}],"predecessor-version":[{"id":85170,"href":"https:\/\/phisonblog.com\/zh\/wp-json\/wp\/v2\/posts\/85146\/revisions\/85170"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/phisonblog.com\/zh\/wp-json\/wp\/v2\/media\/85148"}],"wp:attachment":[{"href":"https:\/\/phisonblog.com\/zh\/wp-json\/wp\/v2\/media?parent=85146"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/phisonblog.com\/zh\/wp-json\/wp\/v2\/categories?post=85146"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/phisonblog.com\/zh\/wp-json\/wp\/v2\/tags?post=85146"}],"curies":[{"name":"\u53ef\u6e7f\u6027\u7c89\u5242","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}