{"id":92691,"date":"2025-05-02T12:33:00","date_gmt":"2025-05-02T03:33:00","guid":{"rendered":"https:\/\/kr-dev.rebellions.ai\/?p=92691"},"modified":"2025-08-21T16:14:56","modified_gmt":"2025-08-21T07:14:56","slug":"atom-max-boosted-performance-for-large-scale-inference","status":"publish","type":"post","link":"https:\/\/dev-rbln-kr.locomotion.co.kr\/?p=92691","title":{"rendered":"ATOM\u2122-Max: Boosted Performance for Large-Scale Inference"},"content":{"rendered":"\n<p class=\"wp-block-paragraph\">As AI workloads grow in complexity and scale, traditional GPU-based systems face mounting challenges in both efficiency and sustainability. Their high power draw and infrastructure demands create bottlenecks for long-term deployment at data center scale. ATOM\u2122-Max addresses this gap with a purpose-built architecture optimized for large-scale inference, offering a more efficient and scalable alternative to general-purpose accelerators. ATOM\u2122-Max ensures high utilization and throughput for the most demanding enterprise and data center AI workloads. Its architectural efficiency not only reduces operational costs but aligns with the increasing need for carbon-aware, performance-per-watt optimized AI infrastructure.<\/p>\n\n\n\n<h2 class=\"wp-block-heading has-large-font-size\"><strong>Scalable, High-Efficiency Inference<\/strong><\/h2>\n\n\n\n<p class=\"wp-block-paragraph\">ATOM\u2122-Max delivers a substantial performance uplift purpose-built for inference at scale, combining exceptional compute throughput with high-bandwidth memory access. With 128 TFLOPS (FP16) and up to 1024 TOPS (INT4), it is engineered to handle the intensive demands of LLMs and AI-driven enterprise workloads. The architecture integrates direct card-to-card communication over PCIe Gen5 x16, enabling fast, low-latency data exchange and efficient horizontal scaling across accelerator nodes. Designed specifically for large-scale inference environments, ATOM\u2122-Max ensures high utilization, predictable latency, and seamless deployment in modern data center infrastructure.<\/p>\n\n\n\n<h2 class=\"wp-block-heading has-large-font-size\"><strong>Total Cost of Ownership (TCO) Challenges<\/strong><\/h2>\n\n\n\n<p class=\"wp-block-paragraph\">Supporting large-scale inference requires balancing throughput, performance-per-watt, and deployment flexibility. Traditional GPU systems incur high CapEx and OpEx, making them difficult to scale sustainably. ATOM\u2122-Max (RBLN-CA25) outperforms its class competitor, L40S, in tokens-per-second per watt (TPS\/W), offering superior performance efficiency in real-world scenarios.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">With high hardware utilization driven by tightly integrated data and memory management, ATOM\u2122-Max minimizes idle overhead and resource waste. This architectural efficiency translates to substantial TCO savings that scale with deployment.<\/p>\n\n\n\n<h2 class=\"wp-block-heading has-large-font-size\"><strong>ATOM\u2122-Max: Scaling Performance-per-Watt<\/strong><\/h2>\n\n\n\n<p class=\"wp-block-paragraph\">Traditional infrastructures face limitations in power efficiency, memory bottlenecks, and deployment costs. ATOM\u2122-Max addresses these challenges.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\" style=\"font-size:26px\"><strong>Scale More, Save More with High Compute Density<\/strong><\/h3>\n\n\n\n<p class=\"wp-block-paragraph\">With 128 TFLOPS FP16 and 1024 TOPS INT4 within a 350W envelope, ATOM\u2122-Max delivers industry-leading efficiency, enabling higher throughput per rack. By significantly reducing server requirements for the same AI workload, it lowers infrastructure costs and optimizes system performance. As workloads increase, economies of scale further amplify cost savings, making ATOM\u2122-Max the ideal choice for high-throughput AI infrastructure at scale.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\" style=\"font-size:26px\"><strong>Hardware-Software Co-optimization<\/strong><\/h3>\n\n\n\n<p class=\"wp-block-paragraph\">Leveraging a co-optimized hardware-software stack, ATOM\u2122-Max maximizes memory efficiency and utilization through an advanced synchronization and shared memory (SHM) scheme. Its compiler autonomously transforms any AI model into highly optimized execution instructions, ensuring peak performance on ATOM\u2122-Max\u2019s specialized architecture while minimizing latency and computational overhead.<\/p>\n\n\n<div class=\"wp-block-image\">\n<figure class=\"aligncenter size-large\"><img decoding=\"async\" src=\"https:\/\/rebellions.ai\/wp-content\/uploads\/2025\/08\/image-21-1024x586.png\" alt=\"\" class=\"wp-image-92498\"\/><figcaption class=\"wp-element-caption\">[High-Density AI Server with ATOM\u2122-Max Accelerators]<\/figcaption><\/figure>\n<\/div>\n\n\n<h2 class=\"wp-block-heading has-large-font-size\"><strong>Built for Tomorrow\u2019s AI<\/strong><\/h2>\n\n\n\n<h3 class=\"wp-block-heading\" style=\"font-size:26px\"><strong>High Bandwidth<\/strong><\/h3>\n\n\n\n<p class=\"wp-block-paragraph\">With 64 GB of high-bandwidth memory and 1024 GB\/s bandwidth, ATOM\u2122-Max delivers the speed and capacity needed to power demanding AI and LLM workloads. Its optimized architecture ensures efficient data flow, maximizing throughput and eliminating bottlenecks in large-scale deployments.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\" style=\"font-size:26px\"><strong>Seamless Scaling<\/strong><\/h3>\n\n\n\n<p class=\"wp-block-paragraph\">Beyond its standalone performance, ATOM\u2122-Max is designed for seamless multi-card scalability. Dedicated intercard cables enable direct high-speed connections between up to eight ATOM\u2122-Max cards, significantly reducing communication overhead and unlocking even greater AI acceleration at scale.<\/p>\n\n\n<div class=\"wp-block-image\">\n<figure class=\"aligncenter size-large\"><img decoding=\"async\" src=\"https:\/\/rebellions.ai\/wp-content\/uploads\/2025\/08\/image-22-1024x874.png\" alt=\"\" class=\"wp-image-92500\"\/><figcaption class=\"wp-element-caption\">High-Speed Connector for Efficient Multi-Card Scaling<\/figcaption><\/figure>\n<\/div>\n\n\n<h2 class=\"wp-block-heading has-large-font-size\"><strong>Conclusion<\/strong><\/h2>\n\n\n\n<p class=\"wp-block-paragraph\">As AI inference demand outgrows training, traditional GPU-based architectures are becoming increasingly inefficient, driving up energy costs, infrastructure overhead, and operational constraints. ATOM\u2122-Max offers a purpose-built alternative, delivering:<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li><strong>Higher compute density for more efficient large-scale inference.<\/strong><\/li>\n\n\n\n<li><strong>Lower power consumption, reducing both TCO and environmental impact.<\/strong><\/li>\n\n\n\n<li><strong>Seamless scalability, ensuring enterprises can deploy future AI models effortlessly.<\/strong><\/li>\n<\/ul>\n\n\n\n<div style=\"height:40px\" aria-hidden=\"true\" class=\"wp-block-spacer\"><\/div>\n\n\n\n<p class=\"wp-block-paragraph\">Power-efficient, high-density AI accelerators like ATOM\u2122-Max will be key to sustainable, cost-effective, and scalable AI deployment.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><\/p>\n","protected":false},"excerpt":{"rendered":"<p>As AI workloads grow in complexity and scale, traditional GPU-based systems face mounting challenges in both efficiency and sustainability. Their&#8230;<\/p>\n","protected":false},"author":8,"featured_media":92720,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"footnotes":""},"categories":[145],"tags":[],"class_list":["post-92691","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-white-papers"],"acf":[],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v25.9 - https:\/\/yoast.com\/wordpress\/plugins\/seo\/ -->\n<title>ATOM\u2122-Max: Boosted Performance for Large-Scale Inference - Rebellions<\/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:\/\/dev-rbln-kr.locomotion.co.kr\/?p=92691\" \/>\n<meta property=\"og:locale\" content=\"ko_KR\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"ATOM\u2122-Max: Boosted Performance for Large-Scale Inference - Rebellions\" \/>\n<meta property=\"og:description\" content=\"As AI workloads grow in complexity and scale, traditional GPU-based systems face mounting challenges in both efficiency and sustainability. Their...\" \/>\n<meta property=\"og:url\" content=\"https:\/\/dev-rbln-kr.locomotion.co.kr\/?p=92691\" \/>\n<meta property=\"og:site_name\" content=\"Rebellions\" \/>\n<meta property=\"article:published_time\" content=\"2025-05-02T03:33:00+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2025-08-21T07:14:56+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/dev-rbln-kr.locomotion.co.kr\/wp-content\/uploads\/2025\/05\/atom-mas.png\" \/>\n\t<meta property=\"og:image:width\" content=\"1054\" \/>\n\t<meta property=\"og:image:height\" content=\"998\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/png\" \/>\n<meta name=\"author\" content=\"jiwon.kwak\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:creator\" content=\"@RebellionsAI\" \/>\n<meta name=\"twitter:site\" content=\"@RebellionsAI\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"https:\/\/dev-rbln-kr.locomotion.co.kr\/?p=92691#article\",\"isPartOf\":{\"@id\":\"https:\/\/dev-rbln-kr.locomotion.co.kr\/?p=92691\"},\"author\":{\"name\":\"jiwon.kwak\",\"@id\":\"https:\/\/dev-rbln-kr.locomotion.co.kr\/#\/schema\/person\/1b946c50a99f04d7b7193c47b212b6c5\"},\"headline\":\"ATOM\u2122-Max: Boosted Performance for Large-Scale Inference\",\"datePublished\":\"2025-05-02T03:33:00+00:00\",\"dateModified\":\"2025-08-21T07:14:56+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\/\/dev-rbln-kr.locomotion.co.kr\/?p=92691\"},\"wordCount\":586,\"publisher\":{\"@id\":\"https:\/\/dev-rbln-kr.locomotion.co.kr\/#organization\"},\"image\":{\"@id\":\"https:\/\/dev-rbln-kr.locomotion.co.kr\/?p=92691#primaryimage\"},\"thumbnailUrl\":\"https:\/\/dev-rbln-kr.locomotion.co.kr\/wp-content\/uploads\/2025\/05\/atom-mas.png\",\"articleSection\":[\"White Papers\"],\"inLanguage\":\"ko-KR\"},{\"@type\":\"WebPage\",\"@id\":\"https:\/\/dev-rbln-kr.locomotion.co.kr\/?p=92691\",\"url\":\"https:\/\/dev-rbln-kr.locomotion.co.kr\/?p=92691\",\"name\":\"ATOM\u2122-Max: Boosted Performance for Large-Scale Inference - Rebellions\",\"isPartOf\":{\"@id\":\"https:\/\/dev-rbln-kr.locomotion.co.kr\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\/\/dev-rbln-kr.locomotion.co.kr\/?p=92691#primaryimage\"},\"image\":{\"@id\":\"https:\/\/dev-rbln-kr.locomotion.co.kr\/?p=92691#primaryimage\"},\"thumbnailUrl\":\"https:\/\/dev-rbln-kr.locomotion.co.kr\/wp-content\/uploads\/2025\/05\/atom-mas.png\",\"datePublished\":\"2025-05-02T03:33:00+00:00\",\"dateModified\":\"2025-08-21T07:14:56+00:00\",\"breadcrumb\":{\"@id\":\"https:\/\/dev-rbln-kr.locomotion.co.kr\/?p=92691#breadcrumb\"},\"inLanguage\":\"ko-KR\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/dev-rbln-kr.locomotion.co.kr\/?p=92691\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"ko-KR\",\"@id\":\"https:\/\/dev-rbln-kr.locomotion.co.kr\/?p=92691#primaryimage\",\"url\":\"https:\/\/dev-rbln-kr.locomotion.co.kr\/wp-content\/uploads\/2025\/05\/atom-mas.png\",\"contentUrl\":\"https:\/\/dev-rbln-kr.locomotion.co.kr\/wp-content\/uploads\/2025\/05\/atom-mas.png\",\"width\":1054,\"height\":998},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/dev-rbln-kr.locomotion.co.kr\/?p=92691#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\/\/dev-rbln-kr.locomotion.co.kr\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"ATOM\u2122-Max: Boosted Performance for Large-Scale Inference\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/dev-rbln-kr.locomotion.co.kr\/#website\",\"url\":\"https:\/\/dev-rbln-kr.locomotion.co.kr\/\",\"name\":\"\\bRebellions\",\"description\":\"Drive AI Innovation. Simple. Fast. At Scale.\",\"publisher\":{\"@id\":\"https:\/\/dev-rbln-kr.locomotion.co.kr\/#organization\"},\"alternateName\":\"\ub9ac\ubca8\ub9ac\uc628\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/dev-rbln-kr.locomotion.co.kr\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"ko-KR\"},{\"@type\":\"Organization\",\"@id\":\"https:\/\/dev-rbln-kr.locomotion.co.kr\/#organization\",\"name\":\"Rebellions\",\"alternateName\":\"\ub9ac\ubca8\ub9ac\uc628\",\"url\":\"https:\/\/dev-rbln-kr.locomotion.co.kr\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"ko-KR\",\"@id\":\"https:\/\/dev-rbln-kr.locomotion.co.kr\/#\/schema\/logo\/image\/\",\"url\":\"https:\/\/dev-rbln-kr.locomotion.co.kr\/wp-content\/uploads\/2023\/02\/Web_Logo_Typing_05.gif\",\"contentUrl\":\"https:\/\/dev-rbln-kr.locomotion.co.kr\/wp-content\/uploads\/2023\/02\/Web_Logo_Typing_05.gif\",\"width\":1920,\"height\":1080,\"caption\":\"Rebellions\"},\"image\":{\"@id\":\"https:\/\/dev-rbln-kr.locomotion.co.kr\/#\/schema\/logo\/image\/\"},\"sameAs\":[\"https:\/\/x.com\/RebellionsAI\",\"https:\/\/www.youtube.com\/@Rebellions_inc\",\"https:\/\/www.linkedin.com\/company\/rebellions-ai\/\"]},{\"@type\":\"Person\",\"@id\":\"https:\/\/dev-rbln-kr.locomotion.co.kr\/#\/schema\/person\/1b946c50a99f04d7b7193c47b212b6c5\",\"name\":\"jiwon.kwak\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"ko-KR\",\"@id\":\"https:\/\/dev-rbln-kr.locomotion.co.kr\/#\/schema\/person\/image\/\",\"url\":\"https:\/\/secure.gravatar.com\/avatar\/bad9ff0489ff35bd54e60b39bd7b60aae7eb336d677d5991a83975ec819e19a4?s=96&d=blank&r=g\",\"contentUrl\":\"https:\/\/secure.gravatar.com\/avatar\/bad9ff0489ff35bd54e60b39bd7b60aae7eb336d677d5991a83975ec819e19a4?s=96&d=blank&r=g\",\"caption\":\"jiwon.kwak\"}}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"ATOM\u2122-Max: Boosted Performance for Large-Scale Inference - Rebellions","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:\/\/dev-rbln-kr.locomotion.co.kr\/?p=92691","og_locale":"ko_KR","og_type":"article","og_title":"ATOM\u2122-Max: Boosted Performance for Large-Scale Inference - Rebellions","og_description":"As AI workloads grow in complexity and scale, traditional GPU-based systems face mounting challenges in both efficiency and sustainability. Their...","og_url":"https:\/\/dev-rbln-kr.locomotion.co.kr\/?p=92691","og_site_name":"Rebellions","article_published_time":"2025-05-02T03:33:00+00:00","article_modified_time":"2025-08-21T07:14:56+00:00","og_image":[{"width":1054,"height":998,"url":"https:\/\/dev-rbln-kr.locomotion.co.kr\/wp-content\/uploads\/2025\/05\/atom-mas.png","type":"image\/png"}],"author":"jiwon.kwak","twitter_card":"summary_large_image","twitter_creator":"@RebellionsAI","twitter_site":"@RebellionsAI","schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/dev-rbln-kr.locomotion.co.kr\/?p=92691#article","isPartOf":{"@id":"https:\/\/dev-rbln-kr.locomotion.co.kr\/?p=92691"},"author":{"name":"jiwon.kwak","@id":"https:\/\/dev-rbln-kr.locomotion.co.kr\/#\/schema\/person\/1b946c50a99f04d7b7193c47b212b6c5"},"headline":"ATOM\u2122-Max: Boosted Performance for Large-Scale Inference","datePublished":"2025-05-02T03:33:00+00:00","dateModified":"2025-08-21T07:14:56+00:00","mainEntityOfPage":{"@id":"https:\/\/dev-rbln-kr.locomotion.co.kr\/?p=92691"},"wordCount":586,"publisher":{"@id":"https:\/\/dev-rbln-kr.locomotion.co.kr\/#organization"},"image":{"@id":"https:\/\/dev-rbln-kr.locomotion.co.kr\/?p=92691#primaryimage"},"thumbnailUrl":"https:\/\/dev-rbln-kr.locomotion.co.kr\/wp-content\/uploads\/2025\/05\/atom-mas.png","articleSection":["White Papers"],"inLanguage":"ko-KR"},{"@type":"WebPage","@id":"https:\/\/dev-rbln-kr.locomotion.co.kr\/?p=92691","url":"https:\/\/dev-rbln-kr.locomotion.co.kr\/?p=92691","name":"ATOM\u2122-Max: Boosted Performance for Large-Scale Inference - Rebellions","isPartOf":{"@id":"https:\/\/dev-rbln-kr.locomotion.co.kr\/#website"},"primaryImageOfPage":{"@id":"https:\/\/dev-rbln-kr.locomotion.co.kr\/?p=92691#primaryimage"},"image":{"@id":"https:\/\/dev-rbln-kr.locomotion.co.kr\/?p=92691#primaryimage"},"thumbnailUrl":"https:\/\/dev-rbln-kr.locomotion.co.kr\/wp-content\/uploads\/2025\/05\/atom-mas.png","datePublished":"2025-05-02T03:33:00+00:00","dateModified":"2025-08-21T07:14:56+00:00","breadcrumb":{"@id":"https:\/\/dev-rbln-kr.locomotion.co.kr\/?p=92691#breadcrumb"},"inLanguage":"ko-KR","potentialAction":[{"@type":"ReadAction","target":["https:\/\/dev-rbln-kr.locomotion.co.kr\/?p=92691"]}]},{"@type":"ImageObject","inLanguage":"ko-KR","@id":"https:\/\/dev-rbln-kr.locomotion.co.kr\/?p=92691#primaryimage","url":"https:\/\/dev-rbln-kr.locomotion.co.kr\/wp-content\/uploads\/2025\/05\/atom-mas.png","contentUrl":"https:\/\/dev-rbln-kr.locomotion.co.kr\/wp-content\/uploads\/2025\/05\/atom-mas.png","width":1054,"height":998},{"@type":"BreadcrumbList","@id":"https:\/\/dev-rbln-kr.locomotion.co.kr\/?p=92691#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/dev-rbln-kr.locomotion.co.kr"},{"@type":"ListItem","position":2,"name":"ATOM\u2122-Max: Boosted Performance for Large-Scale Inference"}]},{"@type":"WebSite","@id":"https:\/\/dev-rbln-kr.locomotion.co.kr\/#website","url":"https:\/\/dev-rbln-kr.locomotion.co.kr\/","name":"\bRebellions","description":"Drive AI Innovation. Simple. Fast. At Scale.","publisher":{"@id":"https:\/\/dev-rbln-kr.locomotion.co.kr\/#organization"},"alternateName":"\ub9ac\ubca8\ub9ac\uc628","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/dev-rbln-kr.locomotion.co.kr\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"ko-KR"},{"@type":"Organization","@id":"https:\/\/dev-rbln-kr.locomotion.co.kr\/#organization","name":"Rebellions","alternateName":"\ub9ac\ubca8\ub9ac\uc628","url":"https:\/\/dev-rbln-kr.locomotion.co.kr\/","logo":{"@type":"ImageObject","inLanguage":"ko-KR","@id":"https:\/\/dev-rbln-kr.locomotion.co.kr\/#\/schema\/logo\/image\/","url":"https:\/\/dev-rbln-kr.locomotion.co.kr\/wp-content\/uploads\/2023\/02\/Web_Logo_Typing_05.gif","contentUrl":"https:\/\/dev-rbln-kr.locomotion.co.kr\/wp-content\/uploads\/2023\/02\/Web_Logo_Typing_05.gif","width":1920,"height":1080,"caption":"Rebellions"},"image":{"@id":"https:\/\/dev-rbln-kr.locomotion.co.kr\/#\/schema\/logo\/image\/"},"sameAs":["https:\/\/x.com\/RebellionsAI","https:\/\/www.youtube.com\/@Rebellions_inc","https:\/\/www.linkedin.com\/company\/rebellions-ai\/"]},{"@type":"Person","@id":"https:\/\/dev-rbln-kr.locomotion.co.kr\/#\/schema\/person\/1b946c50a99f04d7b7193c47b212b6c5","name":"jiwon.kwak","image":{"@type":"ImageObject","inLanguage":"ko-KR","@id":"https:\/\/dev-rbln-kr.locomotion.co.kr\/#\/schema\/person\/image\/","url":"https:\/\/secure.gravatar.com\/avatar\/bad9ff0489ff35bd54e60b39bd7b60aae7eb336d677d5991a83975ec819e19a4?s=96&d=blank&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/bad9ff0489ff35bd54e60b39bd7b60aae7eb336d677d5991a83975ec819e19a4?s=96&d=blank&r=g","caption":"jiwon.kwak"}}]}},"_links":{"self":[{"href":"https:\/\/dev-rbln-kr.locomotion.co.kr\/index.php?rest_route=\/wp\/v2\/posts\/92691","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/dev-rbln-kr.locomotion.co.kr\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/dev-rbln-kr.locomotion.co.kr\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/dev-rbln-kr.locomotion.co.kr\/index.php?rest_route=\/wp\/v2\/users\/8"}],"replies":[{"embeddable":true,"href":"https:\/\/dev-rbln-kr.locomotion.co.kr\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=92691"}],"version-history":[{"count":0,"href":"https:\/\/dev-rbln-kr.locomotion.co.kr\/index.php?rest_route=\/wp\/v2\/posts\/92691\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/dev-rbln-kr.locomotion.co.kr\/index.php?rest_route=\/wp\/v2\/media\/92720"}],"wp:attachment":[{"href":"https:\/\/dev-rbln-kr.locomotion.co.kr\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=92691"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/dev-rbln-kr.locomotion.co.kr\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=92691"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/dev-rbln-kr.locomotion.co.kr\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=92691"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}