{"id":5405,"date":"2023-09-13T13:45:33","date_gmt":"2023-09-13T13:45:33","guid":{"rendered":"https:\/\/dailyai.com\/?p=5405"},"modified":"2023-09-13T13:50:49","modified_gmt":"2023-09-13T13:50:49","slug":"nvidia-software-supercharges-h100-inference-performance","status":"publish","type":"post","link":"https:\/\/dailyai.com\/it\/2023\/09\/nvidia-software-supercharges-h100-inference-performance\/","title":{"rendered":"Il software Nvidia potenzia le prestazioni dell'inferenza H100"},"content":{"rendered":"<p><strong>Nvidia ha annunciato un nuovo software open source che, a suo dire, aumenter\u00e0 le prestazioni di inferenza sulle sue GPU H100.<\/strong><\/p>\n<p>Gran parte dell'attuale domanda di GPU Nvidia riguarda la potenza di calcolo per l'addestramento di nuovi modelli. Ma una volta addestrati, questi modelli devono essere utilizzati. L'inferenza nell'IA si riferisce alla capacit\u00e0 di un LLM come ChatGPT di trarre conclusioni o fare previsioni dai dati su cui \u00e8 stato addestrato e di generare output.<\/p>\n<p>Quando si cerca di usare ChatGPT e appare un messaggio che dice che i suoi server sono sotto sforzo, \u00e8 perch\u00e9 l'hardware di calcolo sta lottando per tenere il passo con la domanda di inferenza.<\/p>\n<p>Nvidia afferma che il suo nuovo software, TensorRT-LLM, pu\u00f2 rendere l'hardware esistente molto pi\u00f9 veloce e pi\u00f9 efficiente dal punto di vista energetico.<\/p>\n<p>Il software include versioni ottimizzate dei modelli pi\u00f9 diffusi, tra cui Meta Llama 2, OpenAI GPT-2 e GPT-3, Falcon, Mosaic MPT e BLOOM.<\/p>\n<p>Utilizza alcune tecniche intelligenti come il batching pi\u00f9 efficiente dei compiti di inferenza e le tecniche di quantizzazione per ottenere un aumento delle prestazioni.<\/p>\n<p>I LLM utilizzano generalmente valori in virgola mobile a 16 bit per rappresentare i pesi e le attivazioni. La quantizzazione prende questi valori e li riduce a valori in virgola mobile a 8 bit durante l'inferenza. La maggior parte dei modelli riesce a mantenere la propria accuratezza con questa precisione ridotta.<\/p>\n<p>Le aziende che dispongono di infrastrutture di calcolo basate sulle GPU H100 di Nvidia possono aspettarsi un enorme miglioramento delle prestazioni di inferenza senza dover spendere un centesimo utilizzando TensorRT-LLM.<\/p>\n<p>Nvidia ha utilizzato un esempio di esecuzione di un piccolo modello open source, GPT-J 6, per riassumere gli articoli del dataset CNN\/Daily Mail. Il suo vecchio chip A100 viene utilizzato come velocit\u00e0 di base e poi confrontato con l'H100 senza e con TensorRT-LLM.<\/p>\n<p><img loading=\"lazy\" decoding=\"async\" class=\"aligncenter wp-image-5412 size-full\" src=\"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/09\/8X-Inference-Performance-Nvidia.jpg\" alt=\"Incremento delle prestazioni di inferenza di Nvidia con TensorRT-LLM\" width=\"832\" height=\"666\" srcset=\"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/09\/8X-Inference-Performance-Nvidia.jpg 832w, https:\/\/dailyai.com\/wp-content\/uploads\/2023\/09\/8X-Inference-Performance-Nvidia-300x240.jpg 300w, https:\/\/dailyai.com\/wp-content\/uploads\/2023\/09\/8X-Inference-Performance-Nvidia-768x615.jpg 768w, https:\/\/dailyai.com\/wp-content\/uploads\/2023\/09\/8X-Inference-Performance-Nvidia-370x296.jpg 370w, https:\/\/dailyai.com\/wp-content\/uploads\/2023\/09\/8X-Inference-Performance-Nvidia-800x640.jpg 800w, https:\/\/dailyai.com\/wp-content\/uploads\/2023\/09\/8X-Inference-Performance-Nvidia-20x16.jpg 20w, https:\/\/dailyai.com\/wp-content\/uploads\/2023\/09\/8X-Inference-Performance-Nvidia-740x592.jpg 740w, https:\/\/dailyai.com\/wp-content\/uploads\/2023\/09\/8X-Inference-Performance-Nvidia-60x48.jpg 60w\" sizes=\"auto, (max-width: 832px) 100vw, 832px\" \/><\/p>\n<p style=\"text-align: center;\">Fonte: <a href=\"https:\/\/developer.nvidia.com\/blog\/nvidia-tensorrt-llm-supercharges-large-language-model-inference-on-nvidia-h100-gpus\/\">Nvidia<\/a><\/p>\n<p>Ed ecco un confronto con Meta's Llama 2<\/p>\n<p><img loading=\"lazy\" decoding=\"async\" class=\"aligncenter wp-image-5413 size-full\" src=\"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/09\/4.6X-Performance-Llama2.jpg\" alt=\"Potenziamento dell&#039;inferenza Nvidia con Llama 2\" width=\"832\" height=\"666\" srcset=\"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/09\/4.6X-Performance-Llama2.jpg 832w, https:\/\/dailyai.com\/wp-content\/uploads\/2023\/09\/4.6X-Performance-Llama2-300x240.jpg 300w, https:\/\/dailyai.com\/wp-content\/uploads\/2023\/09\/4.6X-Performance-Llama2-768x615.jpg 768w, https:\/\/dailyai.com\/wp-content\/uploads\/2023\/09\/4.6X-Performance-Llama2-370x296.jpg 370w, https:\/\/dailyai.com\/wp-content\/uploads\/2023\/09\/4.6X-Performance-Llama2-800x640.jpg 800w, https:\/\/dailyai.com\/wp-content\/uploads\/2023\/09\/4.6X-Performance-Llama2-20x16.jpg 20w, https:\/\/dailyai.com\/wp-content\/uploads\/2023\/09\/4.6X-Performance-Llama2-740x592.jpg 740w, https:\/\/dailyai.com\/wp-content\/uploads\/2023\/09\/4.6X-Performance-Llama2-60x48.jpg 60w\" sizes=\"auto, (max-width: 832px) 100vw, 832px\" \/><\/p>\n<p style=\"text-align: center;\">Fonte: <a href=\"https:\/\/developer.nvidia.com\/blog\/nvidia-tensorrt-llm-supercharges-large-language-model-inference-on-nvidia-h100-gpus\/\">Nvidia<\/a><\/p>\n<p>Nvidia ha dichiarato che i suoi test hanno dimostrato che, a seconda del modello, un H100 con TensorRT-LLM consuma da 3,2 a 5,6 volte meno energia di un A100 durante l'inferenza.<\/p>\n<p>Se si eseguono modelli di intelligenza artificiale su hardware H100, ci\u00f2 significa che non solo le prestazioni di inferenza saranno quasi raddoppiate, ma anche che la bolletta energetica sar\u00e0 molto pi\u00f9 bassa una volta installato questo software.<\/p>\n<p>TensorRT-LLM sar\u00e0 disponibile anche per il sistema Nvidia <a href=\"https:\/\/dailyai.com\/it\/2023\/08\/nvidias-updated-superchip-promises-huge-ai-advancements\/\">Superchip Grace Hopper<\/a> ma l'azienda non ha rilasciato dati sulle prestazioni della GH200 con il nuovo software.<\/p>\n<p>Il nuovo software non era ancora pronto quando Nvidia ha sottoposto il suo Superchip GH200 ai test di benchmarking delle prestazioni MLPerf AI, standard del settore. I risultati hanno mostrato che il GH200 ha ottenuto prestazioni fino a 17% migliori rispetto a un H100 SXM a chip singolo.<\/p>\n<p>Se Nvidia riuscir\u00e0 a ottenere anche solo un modesto incremento delle prestazioni di inferenza utilizzando TensorRT-LLM con il GH200, metter\u00e0 l'azienda davanti ai suoi pi\u00f9 vicini rivali. Essere un rappresentante di Nvidia deve essere il lavoro pi\u00f9 facile del mondo in questo momento.<\/p>","protected":false},"excerpt":{"rendered":"<p>Nvidia ha annunciato un nuovo software open source che, a suo dire, aumenter\u00e0 le prestazioni di inferenza sulle sue GPU H100. Gran parte dell'attuale domanda di GPU Nvidia riguarda la potenza di calcolo per l'addestramento di nuovi modelli. Ma una volta addestrati, questi modelli devono essere utilizzati. L'inferenza nell'IA si riferisce alla capacit\u00e0 di un LLM come ChatGPT di trarre conclusioni o fare previsioni dai dati su cui \u00e8 stato addestrato e di generare output. Quando si tenta di usare ChatGPT e appare un messaggio che dice che i suoi server sono sotto sforzo, \u00e8 perch\u00e9 l'hardware di calcolo sta lottando per tenere il passo con i dati di ChatGPT.<\/p>","protected":false},"author":6,"featured_media":973,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[83],"tags":[99,106],"class_list":["post-5405","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-product","tag-ai-race","tag-nvidia"],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v27.4 - https:\/\/yoast.com\/product\/yoast-seo-wordpress\/ -->\n<title>Nvidia software supercharges H100 inference performance | DailyAI<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/dailyai.com\/it\/2023\/09\/nvidia-software-supercharges-h100-inference-performance\/\" \/>\n<meta property=\"og:locale\" content=\"it_IT\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Nvidia software supercharges H100 inference performance | DailyAI\" \/>\n<meta property=\"og:description\" content=\"Nvidia announced new open source software that it says will supercharge inference performance on its H100 GPUs. A lot of the current demand for Nvidia\u2019s GPUs is to build computing power for training new models. But once trained, those models need to be used. Inference in AI refers to the ability of an LLM like ChatGPT to draw conclusions or make predictions from data it\u2019s been trained on and generate output. When you try to use ChatGPT and a message pops up to say its servers are taking strain, it\u2019s because the computing hardware is struggling to keep up with\" \/>\n<meta property=\"og:url\" content=\"https:\/\/dailyai.com\/it\/2023\/09\/nvidia-software-supercharges-h100-inference-performance\/\" \/>\n<meta property=\"og:site_name\" content=\"DailyAI\" \/>\n<meta property=\"article:published_time\" content=\"2023-09-13T13:45:33+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2023-09-13T13:50:49+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/05\/shutterstock_1742705531.jpg\" \/>\n\t<meta property=\"og:image:width\" content=\"1000\" \/>\n\t<meta property=\"og:image:height\" content=\"667\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/jpeg\" \/>\n<meta name=\"author\" content=\"Eugene van der Watt\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:creator\" content=\"@DailyAIOfficial\" \/>\n<meta name=\"twitter:site\" content=\"@DailyAIOfficial\" \/>\n<meta name=\"twitter:label1\" content=\"Scritto da\" \/>\n\t<meta name=\"twitter:data1\" content=\"Eugene van der Watt\" \/>\n\t<meta name=\"twitter:label2\" content=\"Tempo di lettura stimato\" \/>\n\t<meta name=\"twitter:data2\" content=\"3 minuti\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"NewsArticle\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/09\\\/nvidia-software-supercharges-h100-inference-performance\\\/#article\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/09\\\/nvidia-software-supercharges-h100-inference-performance\\\/\"},\"author\":{\"name\":\"Eugene van der Watt\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/#\\\/schema\\\/person\\\/7ce525c6d0c79838b7cc7cde96993cfa\"},\"headline\":\"Nvidia software supercharges H100 inference performance\",\"datePublished\":\"2023-09-13T13:45:33+00:00\",\"dateModified\":\"2023-09-13T13:50:49+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/09\\\/nvidia-software-supercharges-h100-inference-performance\\\/\"},\"wordCount\":467,\"publisher\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/#organization\"},\"image\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/09\\\/nvidia-software-supercharges-h100-inference-performance\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2023\\\/05\\\/shutterstock_1742705531.jpg\",\"keywords\":[\"AI race\",\"Nvidia\"],\"articleSection\":[\"Product\"],\"inLanguage\":\"it-IT\"},{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/09\\\/nvidia-software-supercharges-h100-inference-performance\\\/\",\"url\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/09\\\/nvidia-software-supercharges-h100-inference-performance\\\/\",\"name\":\"Nvidia software supercharges H100 inference performance | DailyAI\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/09\\\/nvidia-software-supercharges-h100-inference-performance\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/09\\\/nvidia-software-supercharges-h100-inference-performance\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2023\\\/05\\\/shutterstock_1742705531.jpg\",\"datePublished\":\"2023-09-13T13:45:33+00:00\",\"dateModified\":\"2023-09-13T13:50:49+00:00\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/09\\\/nvidia-software-supercharges-h100-inference-performance\\\/#breadcrumb\"},\"inLanguage\":\"it-IT\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/dailyai.com\\\/2023\\\/09\\\/nvidia-software-supercharges-h100-inference-performance\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"it-IT\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/09\\\/nvidia-software-supercharges-h100-inference-performance\\\/#primaryimage\",\"url\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2023\\\/05\\\/shutterstock_1742705531.jpg\",\"contentUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2023\\\/05\\\/shutterstock_1742705531.jpg\",\"width\":1000,\"height\":667,\"caption\":\"nvidia stock\"},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/09\\\/nvidia-software-supercharges-h100-inference-performance\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/dailyai.com\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Nvidia software supercharges H100 inference performance\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/#website\",\"url\":\"https:\\\/\\\/dailyai.com\\\/\",\"name\":\"DailyAI\",\"description\":\"Your Daily Dose of AI News\",\"publisher\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/dailyai.com\\\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"it-IT\"},{\"@type\":\"Organization\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/#organization\",\"name\":\"DailyAI\",\"url\":\"https:\\\/\\\/dailyai.com\\\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"it-IT\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/#\\\/schema\\\/logo\\\/image\\\/\",\"url\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2023\\\/06\\\/Daily-Ai_TL_colour.png\",\"contentUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2023\\\/06\\\/Daily-Ai_TL_colour.png\",\"width\":4501,\"height\":934,\"caption\":\"DailyAI\"},\"image\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/#\\\/schema\\\/logo\\\/image\\\/\"},\"sameAs\":[\"https:\\\/\\\/x.com\\\/DailyAIOfficial\",\"https:\\\/\\\/www.linkedin.com\\\/company\\\/dailyaiofficial\\\/\",\"https:\\\/\\\/www.youtube.com\\\/@DailyAIOfficial\"]},{\"@type\":\"Person\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/#\\\/schema\\\/person\\\/7ce525c6d0c79838b7cc7cde96993cfa\",\"name\":\"Eugene van der Watt\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"it-IT\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2023\\\/07\\\/Eugine_Profile_Picture-96x96.png\",\"url\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2023\\\/07\\\/Eugine_Profile_Picture-96x96.png\",\"contentUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2023\\\/07\\\/Eugine_Profile_Picture-96x96.png\",\"caption\":\"Eugene van der Watt\"},\"description\":\"Eugene comes from an electronic engineering background and loves all things tech. When he takes a break from consuming AI news you'll find him at the snooker table.\",\"sameAs\":[\"www.linkedin.com\\\/in\\\/eugene-van-der-watt-16828119\"],\"url\":\"https:\\\/\\\/dailyai.com\\\/it\\\/author\\\/eugene\\\/\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Il software Nvidia aumenta le prestazioni dell'inferenza H100 | DailyAI","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/dailyai.com\/it\/2023\/09\/nvidia-software-supercharges-h100-inference-performance\/","og_locale":"it_IT","og_type":"article","og_title":"Nvidia software supercharges H100 inference performance | DailyAI","og_description":"Nvidia announced new open source software that it says will supercharge inference performance on its H100 GPUs. A lot of the current demand for Nvidia\u2019s GPUs is to build computing power for training new models. But once trained, those models need to be used. Inference in AI refers to the ability of an LLM like ChatGPT to draw conclusions or make predictions from data it\u2019s been trained on and generate output. When you try to use ChatGPT and a message pops up to say its servers are taking strain, it\u2019s because the computing hardware is struggling to keep up with","og_url":"https:\/\/dailyai.com\/it\/2023\/09\/nvidia-software-supercharges-h100-inference-performance\/","og_site_name":"DailyAI","article_published_time":"2023-09-13T13:45:33+00:00","article_modified_time":"2023-09-13T13:50:49+00:00","og_image":[{"width":1000,"height":667,"url":"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/05\/shutterstock_1742705531.jpg","type":"image\/jpeg"}],"author":"Eugene van der Watt","twitter_card":"summary_large_image","twitter_creator":"@DailyAIOfficial","twitter_site":"@DailyAIOfficial","twitter_misc":{"Scritto da":"Eugene van der Watt","Tempo di lettura stimato":"3 minuti"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"NewsArticle","@id":"https:\/\/dailyai.com\/2023\/09\/nvidia-software-supercharges-h100-inference-performance\/#article","isPartOf":{"@id":"https:\/\/dailyai.com\/2023\/09\/nvidia-software-supercharges-h100-inference-performance\/"},"author":{"name":"Eugene van der Watt","@id":"https:\/\/dailyai.com\/#\/schema\/person\/7ce525c6d0c79838b7cc7cde96993cfa"},"headline":"Nvidia software supercharges H100 inference performance","datePublished":"2023-09-13T13:45:33+00:00","dateModified":"2023-09-13T13:50:49+00:00","mainEntityOfPage":{"@id":"https:\/\/dailyai.com\/2023\/09\/nvidia-software-supercharges-h100-inference-performance\/"},"wordCount":467,"publisher":{"@id":"https:\/\/dailyai.com\/#organization"},"image":{"@id":"https:\/\/dailyai.com\/2023\/09\/nvidia-software-supercharges-h100-inference-performance\/#primaryimage"},"thumbnailUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/05\/shutterstock_1742705531.jpg","keywords":["AI race","Nvidia"],"articleSection":["Product"],"inLanguage":"it-IT"},{"@type":"WebPage","@id":"https:\/\/dailyai.com\/2023\/09\/nvidia-software-supercharges-h100-inference-performance\/","url":"https:\/\/dailyai.com\/2023\/09\/nvidia-software-supercharges-h100-inference-performance\/","name":"Il software Nvidia aumenta le prestazioni dell'inferenza H100 | DailyAI","isPartOf":{"@id":"https:\/\/dailyai.com\/#website"},"primaryImageOfPage":{"@id":"https:\/\/dailyai.com\/2023\/09\/nvidia-software-supercharges-h100-inference-performance\/#primaryimage"},"image":{"@id":"https:\/\/dailyai.com\/2023\/09\/nvidia-software-supercharges-h100-inference-performance\/#primaryimage"},"thumbnailUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/05\/shutterstock_1742705531.jpg","datePublished":"2023-09-13T13:45:33+00:00","dateModified":"2023-09-13T13:50:49+00:00","breadcrumb":{"@id":"https:\/\/dailyai.com\/2023\/09\/nvidia-software-supercharges-h100-inference-performance\/#breadcrumb"},"inLanguage":"it-IT","potentialAction":[{"@type":"ReadAction","target":["https:\/\/dailyai.com\/2023\/09\/nvidia-software-supercharges-h100-inference-performance\/"]}]},{"@type":"ImageObject","inLanguage":"it-IT","@id":"https:\/\/dailyai.com\/2023\/09\/nvidia-software-supercharges-h100-inference-performance\/#primaryimage","url":"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/05\/shutterstock_1742705531.jpg","contentUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/05\/shutterstock_1742705531.jpg","width":1000,"height":667,"caption":"nvidia stock"},{"@type":"BreadcrumbList","@id":"https:\/\/dailyai.com\/2023\/09\/nvidia-software-supercharges-h100-inference-performance\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/dailyai.com\/"},{"@type":"ListItem","position":2,"name":"Nvidia software supercharges H100 inference performance"}]},{"@type":"WebSite","@id":"https:\/\/dailyai.com\/#website","url":"https:\/\/dailyai.com\/","name":"DailyAI","description":"La vostra dose quotidiana di notizie sull'intelligenza artificiale","publisher":{"@id":"https:\/\/dailyai.com\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/dailyai.com\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"it-IT"},{"@type":"Organization","@id":"https:\/\/dailyai.com\/#organization","name":"DailyAI","url":"https:\/\/dailyai.com\/","logo":{"@type":"ImageObject","inLanguage":"it-IT","@id":"https:\/\/dailyai.com\/#\/schema\/logo\/image\/","url":"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/06\/Daily-Ai_TL_colour.png","contentUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/06\/Daily-Ai_TL_colour.png","width":4501,"height":934,"caption":"DailyAI"},"image":{"@id":"https:\/\/dailyai.com\/#\/schema\/logo\/image\/"},"sameAs":["https:\/\/x.com\/DailyAIOfficial","https:\/\/www.linkedin.com\/company\/dailyaiofficial\/","https:\/\/www.youtube.com\/@DailyAIOfficial"]},{"@type":"Person","@id":"https:\/\/dailyai.com\/#\/schema\/person\/7ce525c6d0c79838b7cc7cde96993cfa","name":"Eugene van der Watt","image":{"@type":"ImageObject","inLanguage":"it-IT","@id":"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/07\/Eugine_Profile_Picture-96x96.png","url":"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/07\/Eugine_Profile_Picture-96x96.png","contentUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/07\/Eugine_Profile_Picture-96x96.png","caption":"Eugene van der Watt"},"description":"Eugene proviene da un background di ingegneria elettronica e ama tutto ci\u00f2 che \u00e8 tecnologico. Quando si prende una pausa dal consumo di notizie sull'intelligenza artificiale, lo si pu\u00f2 trovare al tavolo da biliardo.","sameAs":["www.linkedin.com\/in\/eugene-van-der-watt-16828119"],"url":"https:\/\/dailyai.com\/it\/author\/eugene\/"}]}},"_links":{"self":[{"href":"https:\/\/dailyai.com\/it\/wp-json\/wp\/v2\/posts\/5405","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/dailyai.com\/it\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/dailyai.com\/it\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/dailyai.com\/it\/wp-json\/wp\/v2\/users\/6"}],"replies":[{"embeddable":true,"href":"https:\/\/dailyai.com\/it\/wp-json\/wp\/v2\/comments?post=5405"}],"version-history":[{"count":8,"href":"https:\/\/dailyai.com\/it\/wp-json\/wp\/v2\/posts\/5405\/revisions"}],"predecessor-version":[{"id":5417,"href":"https:\/\/dailyai.com\/it\/wp-json\/wp\/v2\/posts\/5405\/revisions\/5417"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/dailyai.com\/it\/wp-json\/wp\/v2\/media\/973"}],"wp:attachment":[{"href":"https:\/\/dailyai.com\/it\/wp-json\/wp\/v2\/media?parent=5405"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/dailyai.com\/it\/wp-json\/wp\/v2\/categories?post=5405"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/dailyai.com\/it\/wp-json\/wp\/v2\/tags?post=5405"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}