{"id":107177,"date":"2023-03-10T12:48:22","date_gmt":"2023-03-10T10:48:23","guid":{"rendered":"https:\/\/prohoster.info\/?p=107177"},"modified":"2023-03-11T11:43:26","modified_gmt":"2023-03-11T09:43:26","slug":"predstavlen-openxla-instrumentarij-dlya-optimizaczii-i-kompilyaczii-modelej-mashinnogo-obucheniya","status":"publish","type":"post","link":"https:\/\/prohoster.info\/cs\/blog\/news\/predstavlen-openxla-instrumentarij-dlya-optimizaczii-i-kompilyaczii-modelej-mashinnogo-obucheniya","title":{"rendered":"Byl p\u0159edstaven OpenXLA, n\u00e1stroj pro optimalizaci a kompilaci model\u016f strojov\u00e9ho u\u010den\u00ed","gt_translate_keys":[{"key":"rendered","format":"text"}]},"content":{"rendered":"<p>Nejv\u011bt\u0161\u00ed spole\u010dnosti zab\u00fdvaj\u00edc\u00ed se v\u00fdvojem v oblasti strojov\u00e9ho u\u010den\u00ed p\u0159edstavily projekt OpenXLA, zam\u011b\u0159en\u00fd na spole\u010dn\u00fd v\u00fdvoj n\u00e1stroj\u016f pro kompilaci a optimalizaci model\u016f pro syst\u00e9my strojov\u00e9ho u\u010den\u00ed. Pod k\u0159\u00eddla projektu p\u0159e\u0161la tak\u00e9 v\u00fdvoj n\u00e1stroj\u016f, kter\u00e9 umo\u017e\u0148uj\u00ed unifikaci kompilace model\u016f p\u0159ipraven\u00fdch ve frameworku TensorFlow, PyTorch a JAX, pro efektivn\u00ed u\u010den\u00ed a prov\u00e1d\u011bn\u00ed na r\u016fzn\u00fdch GPU a specializovan\u00fdch akceler\u00e1torech. Ke spole\u010dn\u00e9 pr\u00e1ci na projektu se p\u0159ipojily spole\u010dnosti jako Google, NVIDIA, AMD, Intel, Meta, Apple, Arm, Alibaba a Amazon.    <\/p>\n<p>O\u010dek\u00e1v\u00e1 se, \u017ee d\u00edky spojen\u00ed sil vedouc\u00edch v\u00fdzkumn\u00fdch t\u00fdm\u016f a z\u00e1stupc\u016f komunity se poda\u0159\u00ed podpo\u0159it rozvoj syst\u00e9m\u016f strojov\u00e9ho u\u010den\u00ed a vy\u0159e\u0161it probl\u00e9m s fragmentac\u00ed infrastruktury pro r\u016fzn\u00e9 frameworky a hardware. OpenXLA umo\u017e\u0148uje efektivn\u00ed podporu r\u016fznorod\u00e9ho hardware, nez\u00e1visle na tom, na jak\u00e9m frameworku byl model strojov\u00e9ho u\u010den\u00ed vytvo\u0159en. O\u010dek\u00e1v\u00e1 se, \u017ee d\u00edky OpenXLA se poda\u0159\u00ed zkr\u00e1tit dobu u\u010den\u00ed model\u016f, zv\u00fd\u0161it propustnost, sn\u00ed\u017eit latenci, sn\u00ed\u017eit n\u00e1klady na v\u00fdpo\u010detn\u00ed zdroje a zkr\u00e1tit \u010das uveden\u00ed produktu na trh.    <center><img decoding=\"async\" alt=\"Byl p\u0159edstaven OpenXLA, n\u00e1stroj pro optimalizaci a kompilaci model\u016f strojov\u00e9ho u\u010den\u00ed\" src=\"\/wp-content\/uploads\/2023\/03\/b684d2f57def6348f6a0037c36baf717.jpg\" style=\"display:block;margin: 0 auto;\" \/><\/center>      <\/p>\n<p>OpenXLA tvo\u0159\u00ed t\u0159i z\u00e1kladn\u00ed komponenty, jejich\u017e k\u00f3d je distribuov\u00e1n pod licenc\u00ed Apache 2.0:  <\/p>\n<ul>\n<li class=\"l\"> XLA (Zrychlen\u00e1 line\u00e1rn\u00ed algebra) \u2014 kompil\u00e1tor, kter\u00fd optimalizuje modely strojov\u00e9ho u\u010den\u00ed pro vysoce v\u00fdkonn\u00e9 prov\u00e1d\u011bn\u00ed na r\u016fzn\u00fdch hardwarov\u00fdch platform\u00e1ch, v\u010detn\u011b GPU, CPU a specializovan\u00fdch akceler\u00e1tor\u016f od r\u016fzn\u00fdch v\u00fdrobc\u016f.\n<li class=\"l\"> StableHLO \u2014 specifikace a z\u00e1kladn\u00ed implementace sady vysoce \u00farov\u0148ov\u00fdch operac\u00ed (HLO, High-Level Operations) pro pou\u017eit\u00ed v modelech syst\u00e9m\u016f strojov\u00e9ho u\u010den\u00ed. P\u016fsob\u00ed jako mezivrstva mezi frameworky strojov\u00e9ho u\u010den\u00ed a kompil\u00e1tory, kter\u00e9 transformuj\u00ed model pro prov\u00e1d\u011bn\u00ed na konkr\u00e9tn\u00edm hardwaru. Mezivrstvy pro generaci model\u016f ve form\u00e1tu StableHLO byly p\u0159ipraveny pro frameworky PyTorch, TensorFlow a JAX. Z\u00e1kladem pro StableHLO je sada MHLO, kter\u00e1 byla roz\u0161\u00ed\u0159ena o podporu serializace a verzov\u00e1n\u00ed.\n<li class=\"l\"> IREE (\u017divotn\u00ed prost\u0159ed\u00ed pro prov\u00e1d\u011bn\u00ed mezip\u0159edstav) \u2014 kompil\u00e1tor a runtime, kter\u00fd transformuje modely strojov\u00e9ho u\u010den\u00ed do univerz\u00e1ln\u00edho mezip\u0159edstav, zalo\u017een\u00e9ho na form\u00e1tu MLIR (V\u00edce\u00farov\u0148ov\u00e1 mezip\u0159edstava) od projektu LLVM. Mezi vlastnosti pat\u0159\u00ed mo\u017enost p\u0159edb\u011b\u017en\u00e9 kompilace, podpora spr\u00e1vy toku, mo\u017enost pou\u017eit\u00ed dynamick\u00fdch prvk\u016f v modelech a optimalizace pro r\u016fzn\u00e9 CPU a GPU s n\u00edzk\u00fdmi re\u017eijn\u00edmi n\u00e1klady.    <\/ul>\n<p>Hlavn\u00ed v\u00fdhody n\u00e1stroje OpenXLA:  <\/p>\n<ul>\n<li class=\"l\"> Dosa\u017een\u00ed optim\u00e1ln\u00edho v\u00fdkonu bez pot\u0159eby hloub\u011bji se pono\u0159it do psan\u00ed k\u00f3du specifick\u00e9ho pro konkr\u00e9tn\u00ed za\u0159\u00edzen\u00ed. Poskytnut\u00ed hotov\u00fdch optimalizac\u00ed, v\u010detn\u011b zjednodu\u0161en\u00ed algebraick\u00fdch v\u00fdraz\u016f, efektivn\u00edho um\u00edst\u011bn\u00ed v pam\u011bti a pl\u00e1nov\u00e1n\u00ed vykon\u00e1v\u00e1n\u00ed s ohledem na sn\u00ed\u017een\u00ed \u0161pi\u010dkov\u00e9 pam\u011b\u0165ov\u00e9 spot\u0159eby a p\u0159et\u00ed\u017een\u00ed.\n<li class=\"l\"> Zjednodu\u0161en\u00ed \u0161k\u00e1lov\u00e1n\u00ed a paralelizace v\u00fdpo\u010dt\u016f. V\u00fdvoj\u00e1\u0159ovi sta\u010d\u00ed p\u0159idat anotace pro podmno\u017einu kritick\u00fdch tenzor\u016f, na jejich\u017e z\u00e1klad\u011b m\u016f\u017ee kompil\u00e1tor automaticky vygenerovat k\u00f3d pro paraleln\u00ed v\u00fdpo\u010dty.\n<li class=\"l\"> Zaji\u0161t\u011bn\u00ed p\u0159enositelnosti d\u00edky podpo\u0159e r\u016fzn\u00fdch hardwarov\u00fdch platforem, jako jsou GPU AMD a NVIDIA, CPU zalo\u017een\u00e9 na architektu\u0159e x86 a ARM, ML akceler\u00e1tory TPU Google, IPU AWS Trainium Inferentia, Graphcore a Cerebras Wafer-Scale Engine.\n<li class=\"l\"> Podpora p\u0159ipojen\u00ed roz\u0161\u00ed\u0159en\u00ed s realizac\u00ed dodate\u010dn\u00fdch funkc\u00ed, jako je podpora psan\u00ed primitiv\u016f hlubok\u00e9ho strojov\u00e9ho u\u010den\u00ed s pou\u017eit\u00edm CUDA, HIP, SYCL, Triton a dal\u0161\u00edch jazyk\u016f pro paraleln\u00ed v\u00fdpo\u010dty. Mo\u017enost ru\u010dn\u00edho lad\u011bn\u00ed \u00fazk\u00fdch m\u00edst v modelech.    <\/ul>\n<p>Zdroj: <a content=\"nofollow\" rel=\"nofollow\" href=\"https:\/\/www.opennet.ru\/opennews\/art.shtml?num=58773\">opennet.ru<\/a> <\/p>","protected":false,"gt_translate_keys":[{"key":"rendered","format":"html"}]},"excerpt":{"rendered":"<p>\u041a\u0440\u0443\u043f\u043d\u0435\u0439\u0448\u0438\u0435 \u043a\u043e\u043c\u043f\u0430\u043d\u0438\u0438, \u0437\u0430\u043d\u0438\u043c\u0430\u044e\u0449\u0438\u0435\u0441\u044f \u0440\u0430\u0437\u0440\u0430\u0431\u043e\u0442\u043a\u043e\u0439 \u0432 \u043e\u0431\u043b\u0430\u0441\u0442\u0438 \u043c\u0430\u0448\u0438\u043d\u043d\u043e\u0433\u043e \u043e\u0431\u0443\u0447\u0435\u043d\u0438\u044f, \u043f\u0440\u0435\u0434\u0441\u0442\u0430\u0432\u0438\u043b\u0438 \u043f\u0440\u043e\u0435\u043a\u0442 OpenXLA, \u043d\u0430\u0446\u0435\u043b\u0435\u043d\u043d\u044b\u0439 \u043d\u0430 \u0441\u043e\u0432\u043c\u0435\u0441\u0442\u043d\u043e\u0435 \u0440\u0430\u0437\u0432\u0438\u0442\u0438\u0435 \u0438\u043d\u0441\u0442\u0440\u0443\u043c\u0435\u043d\u0442\u0430\u0440\u0438\u044f \u0434\u043b\u044f \u043a\u043e\u043c\u043f\u0438\u043b\u044f\u0446\u0438\u0438 \u0438 \u043e\u043f\u0442\u0438\u043c\u0438\u0437\u0430\u0446\u0438\u0438 \u043c\u043e\u0434\u0435\u043b\u0435\u0439 \u0434\u043b\u044f \u0441\u0438\u0441\u0442\u0435\u043c \u043c\u0430\u0448\u0438\u043d\u043d\u043e\u0433\u043e \u043e\u0431\u0443\u0447\u0435\u043d\u0438\u044f. \u041f\u043e\u0434 \u043a\u0440\u044b\u043b\u043e \u043f\u0440\u043e\u0435\u043a\u0442\u0430 \u043f\u0435\u0440\u0435\u0448\u043b\u0430 \u0440\u0430\u0437\u0440\u0430\u0431\u043e\u0442\u043a\u0430 \u0438\u043d\u0441\u0442\u0440\u0443\u043c\u0435\u043d\u0442\u043e\u0432, \u043f\u043e\u0437\u0432\u043e\u043b\u044f\u044e\u0449\u0438\u0445 \u0443\u043d\u0438\u0444\u0438\u0446\u0438\u0440\u043e\u0432\u0430\u0442\u044c \u043a\u043e\u043c\u043f\u0438\u043b\u044f\u0446\u0438\u044e \u043c\u043e\u0434\u0435\u043b\u0435\u0439, \u043f\u043e\u0434\u0433\u043e\u0442\u043e\u0432\u043b\u0435\u043d\u043d\u044b\u0445 \u0432\u043e \u0444\u0440\u0435\u0439\u043c\u0432\u043e\u0440\u043a\u0430\u0445 TensorFlow, PyTorch \u0438 JAX, \u0434\u043b\u044f \u044d\u0444\u0444\u0435\u043a\u0442\u0438\u0432\u043d\u043e\u0433\u043e \u043e\u0431\u0443\u0447\u0435\u043d\u0438\u044f \u0438 \u0432\u044b\u043f\u043e\u043b\u043d\u0435\u043d\u0438\u044f \u043d\u0430 \u0440\u0430\u0437\u043d\u044b\u0445 GPU \u0438 \u0441\u043f\u0435\u0446\u0438\u0430\u043b\u0438\u0437\u0438\u0440\u043e\u0432\u0430\u043d\u043d\u044b\u0445 \u0443\u0441\u043a\u043e\u0440\u0438\u0442\u0435\u043b\u044f\u0445. \u041a \u0441\u043e\u0432\u043c\u0435\u0441\u0442\u043d\u043e\u0439 [&hellip;]<\/p>\n","protected":false,"gt_translate_keys":[{"key":"rendered","format":"html"}]},"author":1,"featured_media":107178,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[702],"tags":[],"class_list":["post-107177","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-news"],"aioseo_notices":[],"aioseo_head":"\n\t\t<!-- All in One SEO 5.0.3 - aioseo.com -->\n\t<meta name=\"description\" content=\"\u041a\u0440\u0443\u043f\u043d\u0435\u0439\u0448\u0438\u0435 \u043a\u043e\u043c\u043f\u0430\u043d\u0438\u0438, \u0437\u0430\u043d\u0438\u043c\u0430\u044e\u0449\u0438\u0435\u0441\u044f \u0440\u0430\u0437\u0440\u0430\u0431\u043e\u0442\u043a\u043e\u0439 \u0432 \u043e\u0431\u043b\u0430\u0441\u0442\u0438 \u043c\u0430\u0448\u0438\u043d\u043d\u043e\u0433\u043e \u043e\u0431\u0443\u0447\u0435\u043d\u0438\u044f, \u043f\u0440\u0435\u0434\u0441\u0442\u0430\u0432\u0438\u043b\u0438 \u043f\u0440\u043e\u0435\u043a\u0442 OpenXLA, \u043d\u0430\u0446\u0435\u043b\u0435\u043d\u043d\u044b\u0439 \u043d\u0430 \u0441\u043e\u0432\u043c\u0435\u0441\u0442\u043d\u043e\u0435 \u0440\u0430\u0437\u0432\u0438\u0442\u0438\u0435 \u0438\u043d\u0441\u0442\u0440\u0443\u043c\u0435\u043d\u0442\u0430\u0440\u0438\u044f \u0434\u043b\u044f \u043a\u043e\u043c\u043f\u0438\u043b\u044f\u0446\u0438\u0438 \u0438 \u043e\u043f\u0442\u0438\u043c\u0438\u0437\u0430\u0446\u0438\u0438 \u043c\u043e\u0434\u0435\u043b\u0435\u0439 \u0434\u043b\u044f \u0441\u0438\u0441\u0442\u0435\u043c \u043c\u0430\u0448\u0438\u043d\u043d\u043e\u0433\u043e.\" \/>\n\t<meta name=\"robots\" content=\"max-image-preview:large\" \/>\n\t<meta name=\"author\" content=\"Yuri Gagarin\"\/>\n\t<link rel=\"canonical\" href=\"https:\/\/prohoster.info\/cs\/blog\/news\/predstavlen-openxla-instrumentarij-dlya-optimizaczii-i-kompilyaczii-modelej-mashinnogo-obucheniya\" \/>\n\t\t<meta name=\"generator\" content=\"All in One SEO (AIOSEO) 5.0.3\" \/>\n\t\t<meta property=\"og:locale\" content=\"cs_CZ\" \/>\n\t\t<meta property=\"og:site_name\" content=\"ProHoster | \u041a\u0443\u043f\u0438\u0442\u044c \u043d\u0430\u0434\u0435\u0436\u043d\u044b\u0439 \u0445\u043e\u0441\u0442\u0438\u043d\u0433 \u0434\u043b\u044f \u0441\u0430\u0439\u0442\u043e\u0432 \u0441 \u0437\u0430\u0449\u0438\u0442\u043e\u0439 \u043e\u0442 DDoS, VPS VDS \u0441\u0435\u0440\u0432\u0435\u0440\u044b\" \/>\n\t\t<meta property=\"og:type\" content=\"article\" \/>\n\t\t<meta property=\"og:title\" content=\"\ud83e\udd47\u041f\u0440\u0435\u0434\u0441\u0442\u0430\u0432\u043b\u0435\u043d OpenXLA, \u0438\u043d\u0441\u0442\u0440\u0443\u043c\u0435\u043d\u0442\u0430\u0440\u0438\u0439 \u0434\u043b\u044f \u043e\u043f\u0442\u0438\u043c\u0438\u0437\u0430\u0446\u0438\u0438 \u0438 \u043a\u043e\u043c\u043f\u0438\u043b\u044f\u0446\u0438\u0438 \u043c\u043e\u0434\u0435\u043b\u0435\u0439 \u043c\u0430\u0448\u0438\u043d\u043d\u043e\u0433\u043e \u043e\u0431\u0443\u0447\u0435\u043d\u0438\u044f | ProHoster\" \/>\n\t\t<meta property=\"og:description\" content=\"\u041a\u0440\u0443\u043f\u043d\u0435\u0439\u0448\u0438\u0435 \u043a\u043e\u043c\u043f\u0430\u043d\u0438\u0438, \u0437\u0430\u043d\u0438\u043c\u0430\u044e\u0449\u0438\u0435\u0441\u044f \u0440\u0430\u0437\u0440\u0430\u0431\u043e\u0442\u043a\u043e\u0439 \u0432 \u043e\u0431\u043b\u0430\u0441\u0442\u0438 \u043c\u0430\u0448\u0438\u043d\u043d\u043e\u0433\u043e \u043e\u0431\u0443\u0447\u0435\u043d\u0438\u044f, \u043f\u0440\u0435\u0434\u0441\u0442\u0430\u0432\u0438\u043b\u0438 \u043f\u0440\u043e\u0435\u043a\u0442 OpenXLA, \u043d\u0430\u0446\u0435\u043b\u0435\u043d\u043d\u044b\u0439 \u043d\u0430 \u0441\u043e\u0432\u043c\u0435\u0441\u0442\u043d\u043e\u0435 \u0440\u0430\u0437\u0432\u0438\u0442\u0438\u0435 \u0438\u043d\u0441\u0442\u0440\u0443\u043c\u0435\u043d\u0442\u0430\u0440\u0438\u044f \u0434\u043b\u044f \u043a\u043e\u043c\u043f\u0438\u043b\u044f\u0446\u0438\u0438 \u0438 \u043e\u043f\u0442\u0438\u043c\u0438\u0437\u0430\u0446\u0438\u0438 \u043c\u043e\u0434\u0435\u043b\u0435\u0439 \u0434\u043b\u044f \u0441\u0438\u0441\u0442\u0435\u043c \u043c\u0430\u0448\u0438\u043d\u043d\u043e\u0433\u043e.\" \/>\n\t\t<meta property=\"og:url\" content=\"https:\/\/prohoster.info\/cs\/blog\/news\/predstavlen-openxla-instrumentarij-dlya-optimizaczii-i-kompilyaczii-modelej-mashinnogo-obucheniya\" \/>\n\t\t<meta property=\"og:image\" content=\"https:\/\/prohoster.info\/wp-content\/uploads\/2021\/11\/logo-350.jpg\" \/>\n\t\t<meta property=\"og:image:secure_url\" content=\"https:\/\/prohoster.info\/wp-content\/uploads\/2021\/11\/logo-350.jpg\" \/>\n\t\t<meta property=\"og:image:width\" content=\"350\" \/>\n\t\t<meta property=\"og:image:height\" content=\"350\" \/>\n\t\t<meta property=\"article:published_time\" content=\"2023-03-10T10:48:23+00:00\" \/>\n\t\t<meta property=\"article:modified_time\" content=\"2023-03-11T09:43:26+00:00\" \/>\n\t\t<meta property=\"article:publisher\" content=\"https:\/\/www.facebook.com\/prohoster\" \/>\n\t\t<meta property=\"article:author\" content=\"https:\/\/www.facebook.com\/prohoster\" \/>\n\t\t<!-- All in One SEO -->\n\n","aioseo_head_json":{"title":"\ud83e\udd47 P\u0159edstaven OpenXLA, n\u00e1stroj pro optimalizaci a kompilaci model\u016f strojov\u00e9ho u\u010den\u00ed | ProHoster","description":"Nejv\u011bt\u0161\u00ed spole\u010dnosti zab\u00fdvaj\u00edc\u00ed se v\u00fdvojem v oblasti strojov\u00e9ho u\u010den\u00ed p\u0159edstavily projekt OpenXLA, zam\u011b\u0159en\u00fd na spole\u010dn\u00fd rozvoj n\u00e1stroje pro kompilaci a optimalizaci model\u016f pro syst\u00e9my strojov\u00e9ho u\u010den\u00ed.","canonical_url":"https:\/\/prohoster.info\/cs\/blog\/news\/predstavlen-openxla-instrumentarij-dlya-optimizaczii-i-kompilyaczii-modelej-mashinnogo-obucheniya","robots":"max-image-preview:large","keywords":"","webmasterTools":{"miscellaneous":""},"schema":null,"og:locale":"cs_CZ","og:site_name":"ProHoster | \u041a\u0443\u043f\u0438\u0442\u044c \u043d\u0430\u0434\u0435\u0436\u043d\u044b\u0439 \u0445\u043e\u0441\u0442\u0438\u043d\u0433 \u0434\u043b\u044f \u0441\u0430\u0439\u0442\u043e\u0432 \u0441 \u0437\u0430\u0449\u0438\u0442\u043e\u0439 \u043e\u0442 DDoS, VPS VDS \u0441\u0435\u0440\u0432\u0435\u0440\u044b","og:type":"article","og:title":"\ud83e\udd47\u041f\u0440\u0435\u0434\u0441\u0442\u0430\u0432\u043b\u0435\u043d OpenXLA, \u0438\u043d\u0441\u0442\u0440\u0443\u043c\u0435\u043d\u0442\u0430\u0440\u0438\u0439 \u0434\u043b\u044f \u043e\u043f\u0442\u0438\u043c\u0438\u0437\u0430\u0446\u0438\u0438 \u0438 \u043a\u043e\u043c\u043f\u0438\u043b\u044f\u0446\u0438\u0438 \u043c\u043e\u0434\u0435\u043b\u0435\u0439 \u043c\u0430\u0448\u0438\u043d\u043d\u043e\u0433\u043e \u043e\u0431\u0443\u0447\u0435\u043d\u0438\u044f | ProHoster","og:description":"\u041a\u0440\u0443\u043f\u043d\u0435\u0439\u0448\u0438\u0435 \u043a\u043e\u043c\u043f\u0430\u043d\u0438\u0438, \u0437\u0430\u043d\u0438\u043c\u0430\u044e\u0449\u0438\u0435\u0441\u044f \u0440\u0430\u0437\u0440\u0430\u0431\u043e\u0442\u043a\u043e\u0439 \u0432 \u043e\u0431\u043b\u0430\u0441\u0442\u0438 \u043c\u0430\u0448\u0438\u043d\u043d\u043e\u0433\u043e \u043e\u0431\u0443\u0447\u0435\u043d\u0438\u044f, \u043f\u0440\u0435\u0434\u0441\u0442\u0430\u0432\u0438\u043b\u0438 \u043f\u0440\u043e\u0435\u043a\u0442 OpenXLA, \u043d\u0430\u0446\u0435\u043b\u0435\u043d\u043d\u044b\u0439 \u043d\u0430 \u0441\u043e\u0432\u043c\u0435\u0441\u0442\u043d\u043e\u0435 \u0440\u0430\u0437\u0432\u0438\u0442\u0438\u0435 \u0438\u043d\u0441\u0442\u0440\u0443\u043c\u0435\u043d\u0442\u0430\u0440\u0438\u044f \u0434\u043b\u044f \u043a\u043e\u043c\u043f\u0438\u043b\u044f\u0446\u0438\u0438 \u0438 \u043e\u043f\u0442\u0438\u043c\u0438\u0437\u0430\u0446\u0438\u0438 \u043c\u043e\u0434\u0435\u043b\u0435\u0439 \u0434\u043b\u044f \u0441\u0438\u0441\u0442\u0435\u043c \u043c\u0430\u0448\u0438\u043d\u043d\u043e\u0433\u043e.","og:url":"https:\/\/prohoster.info\/cs\/blog\/news\/predstavlen-openxla-instrumentarij-dlya-optimizaczii-i-kompilyaczii-modelej-mashinnogo-obucheniya","og:image":"https:\/\/prohoster.info\/wp-content\/uploads\/2021\/11\/logo-350.jpg","og:image:secure_url":"https:\/\/prohoster.info\/wp-content\/uploads\/2021\/11\/logo-350.jpg","og:image:width":350,"og:image:height":350,"article:published_time":"2023-03-10T10:48:23+00:00","article:modified_time":"2023-03-11T09:43:26+00:00","article:publisher":"https:\/\/www.facebook.com\/prohoster","article:author":"https:\/\/www.facebook.com\/prohoster"},"aioseo_meta_data":[],"gt_translate_keys":[{"key":"link","format":"url"}],"_links":{"self":[{"href":"https:\/\/prohoster.info\/cs\/wp-json\/wp\/v2\/posts\/107177","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/prohoster.info\/cs\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/prohoster.info\/cs\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/prohoster.info\/cs\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/prohoster.info\/cs\/wp-json\/wp\/v2\/comments?post=107177"}],"version-history":[{"count":0,"href":"https:\/\/prohoster.info\/cs\/wp-json\/wp\/v2\/posts\/107177\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/prohoster.info\/cs\/wp-json\/wp\/v2\/media\/107178"}],"wp:attachment":[{"href":"https:\/\/prohoster.info\/cs\/wp-json\/wp\/v2\/media?parent=107177"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/prohoster.info\/cs\/wp-json\/wp\/v2\/categories?post=107177"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/prohoster.info\/cs\/wp-json\/wp\/v2\/tags?post=107177"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}