{"id":37279,"date":"2025-02-19T05:25:45","date_gmt":"2025-02-19T05:25:45","guid":{"rendered":"https:\/\/training.linuxfoundation.org\/?p=37279"},"modified":"2025-02-18T15:13:11","modified_gmt":"2025-02-18T15:13:11","slug":"free-webinar-unlocking-the-power-and-speed-of-genai-inference-on-cpus","status":"publish","type":"post","link":"https:\/\/training.linuxfoundation.org\/ja\/blog\/free-webinar-unlocking-the-power-and-speed-of-genai-inference-on-cpus\/","title":{"rendered":"\u7121\u511f\u30a6\u30a7\u30d3\u30ca\u30fc: CPU \u4e0a\u3067 GenAI \u63a8\u8ad6\u306e\u30d1\u30ef\u30fc\u3068\u30b9\u30d4\u30fc\u30c9\u3092\u89e3\u304d\u653e\u3064"},"content":{"rendered":"<h3 style=\"text-align: center;\"><a href=\"https:\/\/hubs.la\/Q035bC800\" target=\"_blank\" rel=\"noopener\"><img loading=\"lazy\" decoding=\"async\" class=\"aligncenter wp-image-37280\" src=\"https:\/\/training.linuxfoundation.org\/wp-content\/uploads\/2025\/02\/GenAI-Webinar-2-300x157.png\" alt=\"\u7121\u511f\u30a6\u30a7\u30d3\u30ca\u30fc: CPU \u4e0a\u3067 GenAI \u63a8\u8ad6\u306e\u30d1\u30ef\u30fc\u3068\u30b9\u30d4\u30fc\u30c9\u3092\u89e3\u304d\u653e\u3064\" width=\"500\" height=\"262\" srcset=\"https:\/\/training.linuxfoundation.org\/wp-content\/uploads\/2025\/02\/GenAI-Webinar-2-300x157.png 300w, https:\/\/training.linuxfoundation.org\/wp-content\/uploads\/2025\/02\/GenAI-Webinar-2-1024x536.png 1024w, https:\/\/training.linuxfoundation.org\/wp-content\/uploads\/2025\/02\/GenAI-Webinar-2-768x402.png 768w, https:\/\/training.linuxfoundation.org\/wp-content\/uploads\/2025\/02\/GenAI-Webinar-2-18x9.png 18w, https:\/\/training.linuxfoundation.org\/wp-content\/uploads\/2025\/02\/GenAI-Webinar-2.png 1200w\" sizes=\"auto, (max-width: 500px) 100vw, 500px\" \/><\/a><em><strong>\u59cb\u3081\u308b\u306e\u304c\u3044\u304b\u306b\u7c21\u5358\u304b\u3092\u77e5\u308b<\/strong><\/em><\/h3>\n<p><strong><a href=\"https:\/\/hubs.la\/Q035bC800\" target=\"_blank\" rel=\"noopener\">\u3053\u3053\u3092\u30af\u30ea\u30c3\u30af<\/a><\/strong> \u3092\u5165\u529b\u3057\u3066\u3001 <strong>Unlocking the Power and Speed of GenAI Inference on CPUs<\/strong>\u3092\u53d7\u8b1b\u3057\u307e\u305b\u3093\u304b\u3002\u3053\u308c\u306f\u30013\u670819\u65e5\u5348\u524d8\u6642PDT\/\u5348\u524d11\u6642EDT\/\u5348\u5f8c4\u6642CET\u306b\u958b\u50ac\u3055\u308c\u308b\u7121\u6599\u30a6\u30a7\u30d3\u30ca\u30fc\u3067\u3059\u3002\u3053\u306e\u30a6\u30a7\u30d3\u30ca\u30fc\u306f <a href=\"https:\/\/training.linuxfoundation.org\/ja\/\" target=\"_blank\" rel=\"noopener\">Linux Foundation Education<\/a> Semiconductor Education Alliance \u3068\u5171\u540c\u3067\u958b\u50ac\u3055\u308c\u3001Arm \u304b\u3089\u306e\u8b1b\u6f14\u8005\u304c\u767b\u5834\u3057\u307e\u3059\u3002<\/p>\n<p>\u30aa\u30fc\u30d7\u30f3\u30bd\u30fc\u30b9\u306eKleidiAI\u30e9\u30a4\u30d6\u30e9\u30ea\u3092\u4f7f\u7528\u3057\u3066CPU\u3092\u6a5f\u68b0\u5b66\u7fd2\u63a8\u8ad6\u306b\u6d3b\u7528\u3059\u308b\u7121\u6599\u306e\u30a6\u30a7\u30d3\u30ca\u30fc\u306b\u3054\u53c2\u52a0\u304f\u3060\u3055\u3044\u3002KleidiAI\u306e\u6700\u9069\u5316\u3055\u308c\u305f\u30de\u30a4\u30af\u30ed\u30ab\u30fc\u30cd\u30eb\u304c\u3059\u3067\u306b\u3069\u306e\u3088\u3046\u306b\u4f7f\u7528\u3055\u308c\u3066\u3044\u308b\u304b\u3092\u5b66\u3073\u3053\u3068\u304c\u3067\u304d\u307e\u3059\u3002 <a href=\"https:\/\/www.arm.com\/products\/development-tools\/embedded-and-software\/kleidi-libraries\" target=\"_blank\" rel=\"noopener\">\u4eba\u6c17\u306eML\u30d5\u30ec\u30fc\u30e0\u30ef\u30fc\u30af\u306b\u63a1\u7528\u3055\u308c\u305f<\/a> PyTorch \u306e\u3088\u3046\u306b\u3001\u958b\u767a\u8005\u306f GPU \u30a2\u30af\u30bb\u30e9\u30ec\u30fc\u30b7\u30e7\u30f3\u306a\u3057\u3067\u9a5a\u7570\u7684\u306a\u63a8\u8ad6\u30d1\u30d5\u30a9\u30fc\u30de\u30f3\u30b9\u3092\u5b9f\u73fe\u3067\u304d\u307e\u3059\u3002<\/p>\n<p>\u307e\u305f\u3001KleidiAI \u3067\u5229\u7528\u3067\u304d\u308b\u4e3b\u8981\u306a\u6700\u9069\u5316\u306b\u3064\u3044\u3066\u3082\u8aac\u660e\u3057\u3001\u5b9f\u969b\u306e\u4f7f\u7528\u4f8b\u3092\u78ba\u8a8d\u3057\u3001\u7c21\u5358\u306b\u958b\u59cb\u3059\u308b\u65b9\u6cd5\u3092\u5b9f\u6f14\u3057\u3066\u3001ML \u5206\u91ce\u3067\u5148\u982d\u306b\u7acb\u3063\u3066\u3001\u3059\u3067\u306b\u6d88\u8cbb\u8005\u306e\u624b\u306b\u6e21\u3063\u3066\u3044\u308b CPU \u306e\u6f5c\u5728\u80fd\u529b\u3092\u6700\u5927\u9650\u306b\u6d3b\u7528\u3067\u304d\u308b\u3088\u3046\u306b\u3057\u307e\u3059\u3002<\/p>\n<p>\u53c2\u52a0\u8005\u306f\u4ee5\u4e0b\u306e\u3053\u3068\u304c\u3067\u304d\u307e\u3059:<\/p>\n<ol>\n<li>\u6700\u8fd1\u30ea\u30ea\u30fc\u30b9\u3055\u308c\u305f\u30aa\u30fc\u30d7\u30f3\u30bd\u30fc\u30b9\u306e KleidiAI \u30e9\u30a4\u30d6\u30e9\u30ea\u304c CPU \u4e0a\u306e\u6a5f\u68b0\u5b66\u7fd2\u63a8\u8ad6\u3092\u3069\u306e\u3088\u3046\u306b\u5f37\u5316\u3059\u308b\u304b\u3092\u5b66\u3073\u307e\u3059\u3002<\/li>\n<li>KleidiAI \u3092\u4f7f\u7528\u3057\u3066 CPU \u306b ML \u30e2\u30c7\u30eb\u3092\u7c21\u5358\u306b\u7d71\u5408\u304a\u3088\u3073\u5c55\u958b\u3059\u308b\u65b9\u6cd5\u3092\u5b66\u3073\u307e\u3059\u3002<\/li>\n<li>\u3059\u3067\u306b\u73fe\u5834\u306b\u3042\u308b\u30c7\u30d0\u30a4\u30b9\u3084\u5c06\u6765\u306e\u30c7\u30d0\u30a4\u30b9\u3067\u306e\u30aa\u30f3\u30c7\u30d0\u30a4\u30b9 ML \u63a8\u8ad6\u306b CPU \u3092\u6d3b\u7528\u3059\u308b\u3053\u3068\u306e\u91cd\u8981\u6027\u3092\u7406\u89e3\u3057\u307e\u3059\u3002<\/li>\n<li>IT \u5b66\u751f\u3068\u958b\u767a\u8005\u5411\u3051\u306b\u8a2d\u8a08\u3055\u308c\u305f\u6559\u80b2\u8cc7\u6599\u306e\u4f7f\u3044\u65b9\u3092\u5b66\u3073\u307e\u3059\u3002<\/li>\n<\/ol>\n<h3 style=\"text-align: center;\"><a href=\"https:\/\/hubs.la\/Q035bC800\" target=\"_blank\" rel=\"noopener\"><strong>\u4eca\u3059\u3050\u767b\u9332\u3057\u3066\u30d1\u30ef\u30fc\u3092\u89e3\u304d\u653e\u3061\u307e\u3057\u3087\u3046!<\/strong><\/a><\/h3>\n<h4><strong>\u30b9\u30d4\u30fc\u30ab\u30fc<\/strong><\/h4>\n<p><strong><a href=\"https:\/\/www.linkedin.com\/in\/gian-marco-iodice-3183a9a1\/\" target=\"_blank\" rel=\"noopener\">Gian Marco Iodice<\/a>\u3001Arm \u4e3b\u5e2d\u30bd\u30d5\u30c8\u30a6\u30a7\u30a2 \u30a8\u30f3\u30b8\u30cb\u30a2<\/strong><br \/>\nGian Marco \u306f\u3001Arm \u306e\u30a8\u30c3\u30b8\u304a\u3088\u3073\u30e2\u30d0\u30a4\u30eb \u30b3\u30f3\u30d4\u30e5\u30fc\u30c6\u30a3\u30f3\u30b0\u306e\u30b9\u30da\u30b7\u30e3\u30ea\u30b9\u30c8\u3067\u3001\u6a5f\u68b0\u5b66\u7fd2 (ML) \u306b\u6ce8\u529b\u3057\u3066\u3044\u307e\u3059\u3002TinyML Cookbook \u306e\u8457\u8005\u3067\u3042\u308a\u3001Arm \u30d7\u30ed\u30bb\u30c3\u30b5\u3067\u306e ML \u30d1\u30d5\u30a9\u30fc\u30de\u30f3\u30b9\u3092\u6700\u9069\u5316\u3059\u308b\u305f\u3081\u306e\u30bd\u30d5\u30c8\u30a6\u30a7\u30a2 \u30e9\u30a4\u30d6\u30e9\u30ea KleidiAI (2024) \u3068 Arm Compute Library (2017) \u3092\u5171\u540c\u3067\u4f5c\u6210\u3057\u307e\u3057\u305f\u3002\u30d4\u30b5\u5927\u5b66 (\u30a4\u30bf\u30ea\u30a2) \u3067\u96fb\u5b50\u5de5\u5b66\u306e\u4fee\u58eb\u53f7\u3092\u512a\u79c0\u306a\u6210\u7e3e\u3067\u53d6\u5f97\u3057\u3001\u7d44\u307f\u8fbc\u307f\u30b7\u30b9\u30c6\u30e0\u306e HW\/SW \u5171\u540c\u8a2d\u8a08\u3092\u5c02\u9580\u3068\u3057\u3066\u3044\u307e\u3059\u3002Arm \u3067\u306f\u3001Generative AI \u306e\u30a8\u30f3\u30b8\u30cb\u30a2\u30ea\u30f3\u30b0\u958b\u767a\u3092\u30ea\u30fc\u30c9\u3057\u3066\u3044\u307e\u3059\u3002<\/p>\n<p><strong><a href=\"https:\/\/www.linkedin.com\/in\/ashoki\/\" target=\"_blank\" rel=\"noopener\">Ashok Bhat<\/a>\u30b7\u30cb\u30a2\u30d7\u30ed\u30c0\u30af\u30c8\u30de\u30cd\u30fc\u30b8\u30e3\u30fc\u3001Arm<\/strong><br \/>\nAshok \u306f Arm \u306e\u30b7\u30cb\u30a2 \u30d7\u30ed\u30c0\u30af\u30c8 \u30de\u30cd\u30fc\u30b8\u30e3\u30fc\u3067\u3001Arm \u30b5\u30fc\u30d0\u30fc\u5411\u3051\u306e PyTorch\u3001TensorFlow\u3001JAX\u3001LLama.cpp\u3001vLLM \u306a\u3069\u306e\u6a5f\u68b0\u5b66\u7fd2\u30d5\u30ec\u30fc\u30e0\u30ef\u30fc\u30af\u306e\u6700\u9069\u5316\u306b\u6ce8\u529b\u3057\u3066\u3044\u307e\u3059\u3002Arm \u306e\u30d1\u30fc\u30c8\u30ca\u30fc\u3068\u5354\u529b\u3057\u3066 ML \u30c6\u30af\u30ce\u30ed\u30b8\u30fc\u3092\u9032\u5316\u3055\u305b\u3001\u30a8\u30b3\u30b7\u30b9\u30c6\u30e0\u5168\u4f53\u306e\u30d1\u30d5\u30a9\u30fc\u30de\u30f3\u30b9\u3092\u5411\u4e0a\u3055\u305b\u3066\u3044\u307e\u3059\u3002<\/p>\n<p><strong>\u30db\u30b9\u30c8\u3092\u52d9\u3081\u308b\u306e\u306f\u3001RX-M Cloud Native &amp; AI Training &amp; Consulting \u30de\u30cd\u30fc\u30b8\u30f3\u30b0 \u30d1\u30fc\u30c8\u30ca\u30fc\u306e <a href=\"http:\/\/linkedin.com\/in\/serewicz\" target=\"_blank\" rel=\"noopener\">Tim Serewicz<\/a>, Linux Foundation, Education\u306eVIce President\u3002 <\/strong><br \/>\nTim \u306f\u3001Linux\u3001\u65b0\u8208\u30c6\u30af\u30ce\u30ed\u30b8\u30fc\u3001\u30aa\u30fc\u30d7\u30f3\u30bd\u30fc\u30b9 \u30d7\u30ed\u30b8\u30a7\u30af\u30c8\u306b\u643a\u308f\u3063\u305f 20 \u5e74\u4ee5\u4e0a\u306e\u7d4c\u9a13\u304c\u3042\u308a\u307e\u3059\u3002\u8ca1\u56e3\u3067\u306f\u3001\u90e8\u9580\u306e\u6226\u7565\u3001\u958b\u767a\u3001\u304a\u3088\u3073\u30b3\u30f3\u30c6\u30f3\u30c4\u306e\u90e8\u9580\u6a2a\u65ad\u7684\u306a\u914d\u4fe1\u3092\u63a8\u9032\u3059\u308b\u307b\u304b\u3001\u30bb\u30ad\u30e5\u30ea\u30c6\u30a3 \u30ca\u30ec\u30c3\u30b8 \u30d5\u30ec\u30fc\u30e0\u30ef\u30fc\u30af \u30c1\u30fc\u30e0\u3092\u7387\u3044\u3066\u3001\u958b\u767a\u8005\u304c\u30b9\u30ad\u30eb\u3092\u7fd2\u5f97\u3057\u3066\u30c6\u30b9\u30c8\u3057\u3001\u4e00\u822c\u7684\u306a\u8106\u5f31\u6027\u3092\u5e38\u306b\u628a\u63e1\u3067\u304d\u308b\u3088\u3046\u306b\u3059\u308b\u305f\u3081\u306e\u30b5\u30a4\u30d0\u30fc\u30bb\u30ad\u30e5\u30ea\u30c6\u30a3 \u30b7\u30ca\u30ea\u30aa\u306e\u30d7\u30e9\u30c3\u30c8\u30d5\u30a9\u30fc\u30e0\u3092\u69cb\u7bc9\u3057\u3066\u3044\u307e\u3059\u3002<\/p>\n<h3 style=\"text-align: center;\"><strong>\u3042\u306a\u305f\u306f <a href=\"https:\/\/hubs.la\/Q035bC800\" target=\"_blank\" rel=\"noopener\">\u767b\u9332<\/a> \u3057\u307e\u3057\u305f\u304b\uff1f<\/strong><\/h3>","protected":false},"excerpt":{"rendered":"<p>\u59cb\u3081\u308b\u306e\u304c\u3044\u304b\u306b\u7c21\u5358\u304b\u3092\u3054\u89a7\u304f\u3060\u3055\u3044\u30023 \u6708 19 \u65e5\u5348\u524d 8 \u6642\u304b\u3089\u958b\u50ac\u3055\u308c\u308b\u7121\u6599\u30a6\u30a7\u30d3\u30ca\u30fc\u300cCPU \u4e0a\u3067\u306e GenAI \u63a8\u8ad6\u306e\u30d1\u30ef\u30fc\u3068\u30b9\u30d4\u30fc\u30c9\u3092\u89e3\u304d\u653e\u3064\u300d\u306b\u4eca\u3059\u3050\u767b\u9332\u3057\u3066\u304f\u3060\u3055\u3044\u3002<\/p>","protected":false},"author":143,"featured_media":37280,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"content-type":"","footnotes":""},"categories":[78],"tags":[],"class_list":["post-37279","post","type-post","status-publish","format-standard","has-post-thumbnail","category-announcements"],"acf":[],"_links":{"self":[{"href":"https:\/\/training.linuxfoundation.org\/ja\/wp-json\/wp\/v2\/posts\/37279","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/training.linuxfoundation.org\/ja\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/training.linuxfoundation.org\/ja\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/training.linuxfoundation.org\/ja\/wp-json\/wp\/v2\/users\/143"}],"replies":[{"embeddable":true,"href":"https:\/\/training.linuxfoundation.org\/ja\/wp-json\/wp\/v2\/comments?post=37279"}],"version-history":[{"count":1,"href":"https:\/\/training.linuxfoundation.org\/ja\/wp-json\/wp\/v2\/posts\/37279\/revisions"}],"predecessor-version":[{"id":37281,"href":"https:\/\/training.linuxfoundation.org\/ja\/wp-json\/wp\/v2\/posts\/37279\/revisions\/37281"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/training.linuxfoundation.org\/ja\/wp-json\/wp\/v2\/media\/37280"}],"wp:attachment":[{"href":"https:\/\/training.linuxfoundation.org\/ja\/wp-json\/wp\/v2\/media?parent=37279"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/training.linuxfoundation.org\/ja\/wp-json\/wp\/v2\/categories?post=37279"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/training.linuxfoundation.org\/ja\/wp-json\/wp\/v2\/tags?post=37279"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}