{"id":2174,"date":"2024-05-07T02:29:02","date_gmt":"2024-05-06T18:29:02","guid":{"rendered":"https:\/\/infernews.com\/?p=2174"},"modified":"2024-05-07T02:29:02","modified_gmt":"2024-05-06T18:29:02","slug":"%e4%bd%bf%e7%94%a8-nvidia-tensorrt-llm-%e5%8f%8a-nvidia-triton-%e6%8f%90%e5%8d%87meta-llama-3%e6%80%a7%e8%83%bd","status":"publish","type":"post","link":"https:\/\/infernews.com\/blog\/%e4%bd%bf%e7%94%a8-nvidia-tensorrt-llm-%e5%8f%8a-nvidia-triton-%e6%8f%90%e5%8d%87meta-llama-3%e6%80%a7%e8%83%bd\/","title":{"rendered":"\u4f7f\u7528 NVIDIA TensorRT-LLM \u53ca NVIDIA Triton \u63d0\u5347Meta Llama 3\u6027\u80fd"},"content":{"rendered":"<div class=\"vlp-link-container vlp-layout-spotlight-clone wp-block-visual-link-preview-link\"><a href=\"https:\/\/developer.nvidia.com\/blog\/turbocharging-meta-llama-3-performance-with-nvidia-tensorrt-llm-and-nvidia-triton-inference-server\" class=\"vlp-link\" title=\"NVIDIA Technical Blog\" rel=\"nofollow\" target=\"_blank\"><\/a><div class=\"vlp-layout-zone-main\"><span class=\"vlp-block-0 vlp-link-title\">NVIDIA Technical Blog<\/span><div class=\"vlp-block-1 vlp-link-summary\">We\u2019re excited to announce support for the Meta Llama 3 family of models in NVIDIA TensorRT-LLM, accelerating and optimizing your LLM inference performance. You can immediately try Llama 3 8B and Llama\u2026<\/div><div class=\"vlp-block-2 vlp-link-image\"><img decoding=\"async\" src=\"https:\/\/developer-blogs.nvidia.com\/wp-content\/uploads\/2024\/04\/dev-llama3-blog-1920x1080-1.png\" style=\"max-width: 1024px; max-height: 1024px\" \/><\/div><\/div><\/div>","protected":false},"excerpt":{"rendered":"","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"googlesitekit_rrm_CAowvqSiDA:productID":"","footnotes":""},"categories":[23],"tags":[],"class_list":["post-2174","post","type-post","status-publish","format-standard","hentry","category-news"],"_links":{"self":[{"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/posts\/2174","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/comments?post=2174"}],"version-history":[{"count":0,"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/posts\/2174\/revisions"}],"wp:attachment":[{"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/media?parent=2174"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/categories?post=2174"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/tags?post=2174"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}