{"id":26564,"date":"2024-11-21T10:19:41","date_gmt":"2024-11-21T10:19:41","guid":{"rendered":"https:\/\/cit.upc.edu\/?post_type=portfolio&p=26564"},"modified":"2025-11-17T13:14:02","modified_gmt":"2025-11-17T13:14:02","slug":"gaissa-an-energy-card-to-assess-and-improve-the-energy-efficiency-and-performance-associated-with-ai","status":"publish","type":"portfolio","link":"https:\/\/cit.upc.edu\/en\/portfolio-item\/gaissa-an-energy-card-to-assess-and-improve-the-energy-efficiency-and-performance-associated-with-ai\/","title":{"rendered":"GAISSA: An energy card to assess and improve energy efficiency and performance of AI"},"content":{"rendered":"\n

22\/11\/2024
Project Header
right
no-repeat;left top;;
auto
20px

Energy consumption in training and inference of artificial intelligence (AI) models, such as large language models (LLMs) like GPT-4, has become a critical challenge due to its environmental impact and the costs associated with high-performance computing (HPC). The energy required to train and interact with these models increases significantly as their size and complexity grow.<\/h4>
Project Header
no-repeat;left top;;
auto
20px


Training an AI model involves feeding its neural networks with large volumes of data and performing multiple iterations to optimise the model\u2019s parameters and enhance its results. These tasks require substantial processing power, leading to considerable electricity consumption. According to Schwartz et al<\/a>., the computational costs of training machine learning (ML) models increased 300,000-fold in just six years (2013\u20132019), doubling every 3.4 months. More recent studies<\/a> indicate that these costs continue to rise at a rate of 2.4 times per year since 2016. If we focus solely on AI systems and consider an intermediate scenario<\/a>, by 2027, data centres and servers hosting AI models are projected to consume between 85 and 134 terawatt hours (TWh) annually. This figure is comparable to the yearly electricity consumption of countries such Argentina, the Netherlands, or Sweden <\/a>and accounts for approximately 0.5% of current global electricity consumption.

However, to fully understand the environmental impact, it is essential to take a holistic view of the ML ecosystem, beyond just model training, and include the operational carbon footprint of ML. Inference – using a trained model to make real-time predictions – can also consume significant energy, particularly in large-scale applications. While the energy consumption for a single inference is much lower than for training, the widespread and continuous use in environments like customer service systems, content generation, or autonomous driving can result in a greater cumulative energy impact. In fact, for services like ChatGPT, inference has been identified as the primary driver of emissions, producing 25 times the carbon emissions required for its training in a single year, according to Chien et al.

This high energy consumption has several implications:\u00a0\u00a0



Economic Costs: Training large-scale models is expensive due to the substantial hardware requirements and the energy needed to power data centres.\u00a0\u00a0

Environmental Impact: Prolonged training with extensive electricity use contributes to carbon emissions, especially when non-renewable energy sources are involved, thereby challenging AI\u2019s sustainability.\u00a0\u00a0

Optimisation: Developing more efficient training and inference methods is crucial, including model optimisation, specialised hardware such as GPUs and TPUs, and strategies like federated learning and model compression.\u00a0\u00a0



In this context, the Software and Service Engineering Group (GESSI) <\/a>at the Universitat Polit\u00e8cnica de Catalunya – Barcelona Tech (UPC) is developing GAISSA, a project that has led to the creation of the GAISSALabel<\/a> software tool. This energy card evaluates the energy efficiency of any machine learning model during both the training and inference phases, making it particularly valuable for HPC services. GAISSALabel can assess the footprint of machine learning models, helping improve efficiency, reduce operational costs, and shorten computation times.\u00a0\u00a0

GAISSALabel will enable AI model developers to:\u00a0\u00a0



Monitor energy consumption and generate detailed reports.\u00a0\u00a0

Identify areas for improvement to reduce energy consumption during the programming of ML model training and inference.\u00a0\u00a0

Optimise models to make them more efficient in terms of time and resources.\u00a0\u00a0



By following the refactoring recommendations provided by GAISSALabel, ML engineers can enhance the energy efficiency of ML systems by up to 50%. This improvement not only leads to economic savings (e.g., lower electricity bills for data centres and HPC facilities), but also reduces the environmental impact of AI applications.\u00a0\u00a0

GAISSALabel offers solutions at three levels:\u00a0\u00a0



Social: Promoting commitment to the energy efficiency of ML systems and empowering end users to select and use sustainable ML solutions.\u00a0\u00a0

For ML software providers: Providing the necessary resources to develop sustainable ML systems, supported by management and reporting tools aligned with regulatory requirements.

Individual: Assisting data scientists and ML engineers in understanding and managing energy efficiency in production by raising awareness and providing insights into the energy consumption of ML systems and tools.



The project began in December 2022 and is scheduled to conclude in September 2025, with a total budget of \u20ac277,035.00. It is funded by the Ministry of Science and Innovation and Universities, along with contributions from the Next Generation EU Funds.
Main Text
no-repeat;left top;;
auto


\"GAISSA_Project_1500x500\"
full
https:\/\/gaissa.upc.edu\/en<\/a>
contain
center center
center
hide

\"image-800-a14b0fd9ec48658b4d99c650fd85c955\"
full
https:\/\/gaissa.upc.edu\/en<\/a>
contain
center center
center
hide

GK4DBUwxWDQ
autoplay=1&loop=1
contain
center center
hide

Technology<\/h5>

Digital Transformation<\/a>

Energy<\/a>
Tecnolog\u00eda
no-repeat;left top;;
auto
0px

25

Sector<\/h5>

Energy<\/a>
Sector
no-repeat;left top;;
auto
0px

25

Topic<\/h5>

Artificial Intelligence<\/a>

Big Data<\/a>
Tema
no-repeat;left top;;
auto
30px

40

You want to know more?<\/h5>
Contact Button
no-repeat;left top;;
auto
0px

\n

Button<\/span><\/a>\n



\n

Button<\/span><\/a>\n
no-repeat;left top;;
auto

50

Related Projects<\/h4>
Proyectos Relacionados
no-repeat;left top;;
auto

4
grid
4
date
DESC

<\/p>\n","protected":false},"excerpt":{"rendered":"

Energy consumption in training and inference of artificial intelligence (AI) models, such as large language models (LLMs) like GPT-4, has become a critical challenge due to its environmental impact and the costs associated with high-performance computing (HPC). The energy required to train these models and interact with them increases significantly as the models grow in size and complexity. <\/p>\n","protected":false},"author":5,"featured_media":26614,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":[],"portfolio-types":[929,930,391,223],"class_list":["post-26564","portfolio","type-portfolio","status-publish","has-post-thumbnail","hentry","portfolio-types-bd-en","portfolio-types-ia-en","portfolio-types-energia-en","portfolio-types-tecnologias-de-las-tic-en"],"yoast_head":"\nGAISSA: Energy card to improve the AI efficiency and performance - CIT UPC<\/title>\n<meta name=\"description\" content=\"Energy consumption in training and inference of artificial intelligence (AI) models, such as large language models (LLMs) like GPT-4, has become a critical challenge due to its environmental impact and the costs associated with high-performance computing (HPC). The energy required to train these models and interact with them increases significantly as the models grow in size and complexity.\" \/>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/cit.upc.edu\/es\/portfolio-item\/gaissa-una-tarjeta-energetica-para-evaluar-y-mejorar-la-eficiencia-energetica-y-el-rendimiento-asociados-a-la-ia\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"GAISSA: Energy card to improve the AI efficiency and performance - CIT UPC\" \/>\n<meta property=\"og:description\" content=\"Energy consumption in training and inference of artificial intelligence (AI) models, such as large language models (LLMs) like GPT-4, has become a critical challenge due to its environmental impact and the costs associated with high-performance computing (HPC). The energy required to train these models and interact with them increases significantly as the models grow in size and complexity.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/cit.upc.edu\/es\/portfolio-item\/gaissa-una-tarjeta-energetica-para-evaluar-y-mejorar-la-eficiencia-energetica-y-el-rendimiento-asociados-a-la-ia\/\" \/>\n<meta property=\"og:site_name\" content=\"CIT UPC\" \/>\n<meta property=\"article:publisher\" content=\"https:\/\/www.facebook.com\/cit.upc\" \/>\n<meta property=\"article:modified_time\" content=\"2025-11-17T13:14:02+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/cit.upc.edu\/wp-content\/uploads\/2024\/11\/gaissa700x526-2.png\" \/>\n\t<meta property=\"og:image:width\" content=\"700\" \/>\n\t<meta property=\"og:image:height\" content=\"526\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/png\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:site\" content=\"@CIT_UPC\" \/>\n<meta name=\"twitter:label1\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data1\" content=\"5 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/cit.upc.edu\\\/es\\\/portfolio-item\\\/gaissa-una-tarjeta-energetica-para-evaluar-y-mejorar-la-eficiencia-energetica-y-el-rendimiento-asociados-a-la-ia\\\/\",\"url\":\"https:\\\/\\\/cit.upc.edu\\\/es\\\/portfolio-item\\\/gaissa-una-tarjeta-energetica-para-evaluar-y-mejorar-la-eficiencia-energetica-y-el-rendimiento-asociados-a-la-ia\\\/\",\"name\":\"GAISSA: Energy card to improve the AI efficiency and performance - CIT UPC\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/cit.upc.edu\\\/es\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/cit.upc.edu\\\/es\\\/portfolio-item\\\/gaissa-una-tarjeta-energetica-para-evaluar-y-mejorar-la-eficiencia-energetica-y-el-rendimiento-asociados-a-la-ia\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/cit.upc.edu\\\/es\\\/portfolio-item\\\/gaissa-una-tarjeta-energetica-para-evaluar-y-mejorar-la-eficiencia-energetica-y-el-rendimiento-asociados-a-la-ia\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/cit.upc.edu\\\/wp-content\\\/uploads\\\/2024\\\/11\\\/gaissa700x526-2.png\",\"datePublished\":\"2024-11-21T10:19:41+00:00\",\"dateModified\":\"2025-11-17T13:14:02+00:00\",\"description\":\"Energy consumption in training and inference of artificial intelligence (AI) models, such as large language models (LLMs) like GPT-4, has become a critical challenge due to its environmental impact and the costs associated with high-performance computing (HPC). The energy required to train these models and interact with them increases significantly as the models grow in size and complexity.\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/cit.upc.edu\\\/es\\\/portfolio-item\\\/gaissa-una-tarjeta-energetica-para-evaluar-y-mejorar-la-eficiencia-energetica-y-el-rendimiento-asociados-a-la-ia\\\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/cit.upc.edu\\\/es\\\/portfolio-item\\\/gaissa-una-tarjeta-energetica-para-evaluar-y-mejorar-la-eficiencia-energetica-y-el-rendimiento-asociados-a-la-ia\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/cit.upc.edu\\\/es\\\/portfolio-item\\\/gaissa-una-tarjeta-energetica-para-evaluar-y-mejorar-la-eficiencia-energetica-y-el-rendimiento-asociados-a-la-ia\\\/#primaryimage\",\"url\":\"https:\\\/\\\/cit.upc.edu\\\/wp-content\\\/uploads\\\/2024\\\/11\\\/gaissa700x526-2.png\",\"contentUrl\":\"https:\\\/\\\/cit.upc.edu\\\/wp-content\\\/uploads\\\/2024\\\/11\\\/gaissa700x526-2.png\",\"width\":700,\"height\":526},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/cit.upc.edu\\\/es\\\/portfolio-item\\\/gaissa-una-tarjeta-energetica-para-evaluar-y-mejorar-la-eficiencia-energetica-y-el-rendimiento-asociados-a-la-ia\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Cover page\",\"item\":\"https:\\\/\\\/cit.upc.edu\\\/en\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"GAISSA: An energy card to assess and improve energy efficiency and performance of AI\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/cit.upc.edu\\\/es\\\/#website\",\"url\":\"https:\\\/\\\/cit.upc.edu\\\/es\\\/\",\"name\":\"CIT UPC\",\"description\":\"Centro de Innovaci\u00f3n y Tecnolog\u00eda\",\"publisher\":{\"@id\":\"https:\\\/\\\/cit.upc.edu\\\/es\\\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/cit.upc.edu\\\/es\\\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"},{\"@type\":\"Organization\",\"@id\":\"https:\\\/\\\/cit.upc.edu\\\/es\\\/#organization\",\"name\":\"CIT UPC - UPC Technology Center\",\"url\":\"https:\\\/\\\/cit.upc.edu\\\/es\\\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/cit.upc.edu\\\/es\\\/#\\\/schema\\\/logo\\\/image\\\/\",\"url\":\"https:\\\/\\\/cit.upc.edu\\\/wp-content\\\/uploads\\\/2020\\\/04\\\/cropped-logo_positiu_horitzontal_2020_espanol.png\",\"contentUrl\":\"https:\\\/\\\/cit.upc.edu\\\/wp-content\\\/uploads\\\/2020\\\/04\\\/cropped-logo_positiu_horitzontal_2020_espanol.png\",\"width\":512,\"height\":512,\"caption\":\"CIT UPC - UPC Technology Center\"},\"image\":{\"@id\":\"https:\\\/\\\/cit.upc.edu\\\/es\\\/#\\\/schema\\\/logo\\\/image\\\/\"},\"sameAs\":[\"https:\\\/\\\/www.facebook.com\\\/cit.upc\",\"https:\\\/\\\/x.com\\\/CIT_UPC\",\"https:\\\/\\\/www.youtube.com\\\/user\\\/CITUPC\",\"https:\\\/\\\/www.flickr.com\\\/photos\\\/181927091@N08\",\"https:\\\/\\\/www.linkedin.com\\\/company\\\/cit-upc\\\/\",\"https:\\\/\\\/www.instagram.com\\\/cit_upc\\\/\"]}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"GAISSA: Energy card to improve the AI efficiency and performance - CIT UPC","description":"Energy consumption in training and inference of artificial intelligence (AI) models, such as large language models (LLMs) like GPT-4, has become a critical challenge due to its environmental impact and the costs associated with high-performance computing (HPC). The energy required to train these models and interact with them increases significantly as the models grow in size and complexity.","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:\/\/cit.upc.edu\/es\/portfolio-item\/gaissa-una-tarjeta-energetica-para-evaluar-y-mejorar-la-eficiencia-energetica-y-el-rendimiento-asociados-a-la-ia\/","og_locale":"en_US","og_type":"article","og_title":"GAISSA: Energy card to improve the AI efficiency and performance - CIT UPC","og_description":"Energy consumption in training and inference of artificial intelligence (AI) models, such as large language models (LLMs) like GPT-4, has become a critical challenge due to its environmental impact and the costs associated with high-performance computing (HPC). The energy required to train these models and interact with them increases significantly as the models grow in size and complexity.","og_url":"https:\/\/cit.upc.edu\/es\/portfolio-item\/gaissa-una-tarjeta-energetica-para-evaluar-y-mejorar-la-eficiencia-energetica-y-el-rendimiento-asociados-a-la-ia\/","og_site_name":"CIT UPC","article_publisher":"https:\/\/www.facebook.com\/cit.upc","article_modified_time":"2025-11-17T13:14:02+00:00","og_image":[{"width":700,"height":526,"url":"https:\/\/cit.upc.edu\/wp-content\/uploads\/2024\/11\/gaissa700x526-2.png","type":"image\/png"}],"twitter_card":"summary_large_image","twitter_site":"@CIT_UPC","twitter_misc":{"Est. reading time":"5 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/cit.upc.edu\/es\/portfolio-item\/gaissa-una-tarjeta-energetica-para-evaluar-y-mejorar-la-eficiencia-energetica-y-el-rendimiento-asociados-a-la-ia\/","url":"https:\/\/cit.upc.edu\/es\/portfolio-item\/gaissa-una-tarjeta-energetica-para-evaluar-y-mejorar-la-eficiencia-energetica-y-el-rendimiento-asociados-a-la-ia\/","name":"GAISSA: Energy card to improve the AI efficiency and performance - CIT UPC","isPartOf":{"@id":"https:\/\/cit.upc.edu\/es\/#website"},"primaryImageOfPage":{"@id":"https:\/\/cit.upc.edu\/es\/portfolio-item\/gaissa-una-tarjeta-energetica-para-evaluar-y-mejorar-la-eficiencia-energetica-y-el-rendimiento-asociados-a-la-ia\/#primaryimage"},"image":{"@id":"https:\/\/cit.upc.edu\/es\/portfolio-item\/gaissa-una-tarjeta-energetica-para-evaluar-y-mejorar-la-eficiencia-energetica-y-el-rendimiento-asociados-a-la-ia\/#primaryimage"},"thumbnailUrl":"https:\/\/cit.upc.edu\/wp-content\/uploads\/2024\/11\/gaissa700x526-2.png","datePublished":"2024-11-21T10:19:41+00:00","dateModified":"2025-11-17T13:14:02+00:00","description":"Energy consumption in training and inference of artificial intelligence (AI) models, such as large language models (LLMs) like GPT-4, has become a critical challenge due to its environmental impact and the costs associated with high-performance computing (HPC). The energy required to train these models and interact with them increases significantly as the models grow in size and complexity.","breadcrumb":{"@id":"https:\/\/cit.upc.edu\/es\/portfolio-item\/gaissa-una-tarjeta-energetica-para-evaluar-y-mejorar-la-eficiencia-energetica-y-el-rendimiento-asociados-a-la-ia\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/cit.upc.edu\/es\/portfolio-item\/gaissa-una-tarjeta-energetica-para-evaluar-y-mejorar-la-eficiencia-energetica-y-el-rendimiento-asociados-a-la-ia\/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/cit.upc.edu\/es\/portfolio-item\/gaissa-una-tarjeta-energetica-para-evaluar-y-mejorar-la-eficiencia-energetica-y-el-rendimiento-asociados-a-la-ia\/#primaryimage","url":"https:\/\/cit.upc.edu\/wp-content\/uploads\/2024\/11\/gaissa700x526-2.png","contentUrl":"https:\/\/cit.upc.edu\/wp-content\/uploads\/2024\/11\/gaissa700x526-2.png","width":700,"height":526},{"@type":"BreadcrumbList","@id":"https:\/\/cit.upc.edu\/es\/portfolio-item\/gaissa-una-tarjeta-energetica-para-evaluar-y-mejorar-la-eficiencia-energetica-y-el-rendimiento-asociados-a-la-ia\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Cover page","item":"https:\/\/cit.upc.edu\/en\/"},{"@type":"ListItem","position":2,"name":"GAISSA: An energy card to assess and improve energy efficiency and performance of AI"}]},{"@type":"WebSite","@id":"https:\/\/cit.upc.edu\/es\/#website","url":"https:\/\/cit.upc.edu\/es\/","name":"CIT UPC","description":"Centro de Innovaci\u00f3n y Tecnolog\u00eda","publisher":{"@id":"https:\/\/cit.upc.edu\/es\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/cit.upc.edu\/es\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"},{"@type":"Organization","@id":"https:\/\/cit.upc.edu\/es\/#organization","name":"CIT UPC - UPC Technology Center","url":"https:\/\/cit.upc.edu\/es\/","logo":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/cit.upc.edu\/es\/#\/schema\/logo\/image\/","url":"https:\/\/cit.upc.edu\/wp-content\/uploads\/2020\/04\/cropped-logo_positiu_horitzontal_2020_espanol.png","contentUrl":"https:\/\/cit.upc.edu\/wp-content\/uploads\/2020\/04\/cropped-logo_positiu_horitzontal_2020_espanol.png","width":512,"height":512,"caption":"CIT UPC - UPC Technology Center"},"image":{"@id":"https:\/\/cit.upc.edu\/es\/#\/schema\/logo\/image\/"},"sameAs":["https:\/\/www.facebook.com\/cit.upc","https:\/\/x.com\/CIT_UPC","https:\/\/www.youtube.com\/user\/CITUPC","https:\/\/www.flickr.com\/photos\/181927091@N08","https:\/\/www.linkedin.com\/company\/cit-upc\/","https:\/\/www.instagram.com\/cit_upc\/"]}]}},"_links":{"self":[{"href":"https:\/\/cit.upc.edu\/en\/wp-json\/wp\/v2\/portfolio\/26564","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/cit.upc.edu\/en\/wp-json\/wp\/v2\/portfolio"}],"about":[{"href":"https:\/\/cit.upc.edu\/en\/wp-json\/wp\/v2\/types\/portfolio"}],"author":[{"embeddable":true,"href":"https:\/\/cit.upc.edu\/en\/wp-json\/wp\/v2\/users\/5"}],"replies":[{"embeddable":true,"href":"https:\/\/cit.upc.edu\/en\/wp-json\/wp\/v2\/comments?post=26564"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/cit.upc.edu\/en\/wp-json\/wp\/v2\/media\/26614"}],"wp:attachment":[{"href":"https:\/\/cit.upc.edu\/en\/wp-json\/wp\/v2\/media?parent=26564"}],"wp:term":[{"taxonomy":"portfolio-types","embeddable":true,"href":"https:\/\/cit.upc.edu\/en\/wp-json\/wp\/v2\/portfolio-types?post=26564"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}