{"id":1834,"date":"2026-06-28T07:29:05","date_gmt":"2026-06-28T07:29:05","guid":{"rendered":"https:\/\/rdp.in\/gpu-mart\/?post_type=product&#038;p=1834"},"modified":"2026-07-05T09:21:18","modified_gmt":"2026-07-05T09:21:18","slug":"draco-250-kw-in-rack-cdu","status":"publish","type":"product","link":"https:\/\/rdp.in\/gpu-mart\/product\/draco-250-kw-in-rack-cdu\/","title":{"rendered":"DRACO 250 kW In-Rack CDU"},"content":{"rendered":"<p>The DRACO 250 kW In-Rack CDU removes the heat that dense GPU racks generate \u2014 250 kW of cooling via liquid-to-liquid cdu (in-rack), so today&#8217;s 700 W\u20131 kW+ GPUs run at full clocks without thermal throttling. It is the thermal layer that makes high-density AI racks possible on-premises, in INR, on a GST invoice.<\/p>\n<p>Engineered to match RDP&#8217;s GPU servers, rack-scale systems and superclusters, it integrates with your facility water or runs closed-loop, and is delivered sized, plumbed and validated with the compute it cools \u2014 with leak detection and monitoring built in.<\/p>\n<h3>Key highlights<\/h3>\n<ul>\n<li><strong>250 kW<\/strong> \u2014 rack\/row-level coolant distribution.<\/li>\n<li><strong>Liquid-to-liquid CDU (in-rack)<\/strong> \u2014 distributes treated coolant to cold-plate loops with filtration and control.<\/li>\n<li><strong>Up to 400 L\/min \u00b7 PG25 \/ treated water<\/strong> \u2014 controlled flow and coolant chemistry for reliable, corrosion-safe operation.<\/li>\n<li><strong>Leak detection &amp; monitoring<\/strong> \u2014 sensors and BMS\/DCIM integration for safe, observable operation.<\/li>\n<li><strong>Supports 1-2 dense racks<\/strong> \u2014 sized to the density of RDP GPU racks.<\/li>\n<li><strong>Quiet, efficient<\/strong> \u2014 liquid moves heat far more efficiently than air, lowering fan power and PUE.<\/li>\n<li><strong>Validated with RDP compute<\/strong> \u2014 delivered as part of a tested, cooled rack.<\/li>\n<li><strong>Make-in-India OEM<\/strong> \u2014 predictable INR pricing, GST tax invoice, pan-India onsite support, GeM-procurable.<\/li>\n<\/ul>\n<h3>Where it fits<\/h3>\n<ul>\n<li><strong>Dense GPU racks (primary):<\/strong> feeds direct-to-chip cold-plate loops across a rack or row.<\/li>\n<li><strong>Rack-scale &amp; NVL systems:<\/strong> the cooling that keeps NVL72-class racks within thermal limits.<\/li>\n<li><strong>Retrofit or new build:<\/strong> design a liquid-cooled hall, or add density to a room.<\/li>\n<li><strong>Edge\/micro-DC:<\/strong> sealed\/compact options for self-contained sites.<\/li>\n<\/ul>\n<h3>How it works<\/h3>\n<p>The unit isolates the rack coolant loop from facility water, controls flow, temperature and pressure, filters the coolant, and distributes it to the cold-plate loops. RDP sizes the loop, flow and coolant to your rack density and facility. <em>Honest note: real cooling capacity depends on inlet water temperature, flow and rack layout \u2014 we size and validate it for your room.<\/em><\/p>\n<h3>Industry use cases<\/h3>\n<ul>\n<li><strong>AI data centres<\/strong> \u2014 cool dense GPU and NVL racks at full clocks.<\/li>\n<li><strong>Government &amp; national labs<\/strong> \u2014 sovereign HPC\/AI cooling.<\/li>\n<li><strong>Neocloud \/ AI providers<\/strong> \u2014 higher density per rack, lower PUE.<\/li>\n<li><strong>Manufacturing &amp; energy<\/strong> \u2014 HPC + AI thermal management.<\/li>\n<li><strong>Edge &amp; remote sites<\/strong> \u2014 sealed liquid cooling without a facility loop.<\/li>\n<li><strong>Colocation<\/strong> \u2014 liquid-ready density in shared halls.<\/li>\n<\/ul>\n<h3>Performance \u2014 and how to be sure<\/h3>\n<p>We don&#8217;t publish inflated peak numbers. The honest picture: 250 kW at Up to 400 L\/min cools dense AI racks within thermal limits given suitable conditions. <strong>Want certainty? Request a thermal assessment of your racks and room before you buy<\/strong>; we&#8217;ll size the solution and confirm the cooling capacity at your conditions.<\/p>\n<h3>Series &amp; scale path<\/h3>\n<ul>\n<li><strong>DRACO<\/strong> (flagship thermal tier) \u2014 <em>this<\/em>.<\/li>\n<li><strong>Capacity ladder:<\/strong> rear-door HX \u2192 in-rack\/in-row CDU \u2192 row CDU \u2192 facility CDU (MW-scale).<\/li>\n<li><strong>When to step up:<\/strong> grow from rack to row to facility cooling as density rises \u2014 talk to an architect about the loop.<\/li>\n<\/ul>\n<h3>Liquid vs air \u2014 the efficiency case<\/h3>\n<p>At 700 W\u20131 kW+ per GPU, air cooling hits its limit; liquid removes heat far more efficiently, enabling higher density, full clocks and lower PUE \u2014 and quieter rooms. The result is more compute per rack and lower energy cost. RDP pricing is fixed in INR with a GST input-credit-eligible invoice \u2014 ask for a <strong>PUE and density comparison<\/strong> for your room.<\/p>\n<h3>Software &amp; integration<\/h3>\n<p>Integrates with your facility: BMS\/DCIM monitoring, leak detection, flow\/temperature\/pressure telemetry, and alarms. Designed to match RDP GPU servers, rack-scale systems and superclusters.<\/p>\n<h3>Power, cooling &amp; facility integration<\/h3>\n<p>A In-rack (full-height) unit \u2014 plan facility water (supply\/return temperature and flow), power for pumps\/controls, and floor\/rack integration. <em>(Exact capacity, flow, pressure-drop and connection figures confirmed in the thermal design.)<\/em> Redundant pumps and monitoring available.<\/p>\n<h3>Deployment, warranty &amp; support<\/h3>\n<ul>\n<li><strong>Made to order<\/strong>, sized, plumbed and commissioned in India with the compute it cools; lead time confirmed at quote.<\/li>\n<li><strong>In the box:<\/strong> CDU, fittings, sensors and controls; facility connection scoped at quote.<\/li>\n<li><strong>Onsite warranty + AMC<\/strong> with pan-India coverage and an RMA\/escalation path <em>(exact terms confirmed at quote)<\/em>.<\/li>\n<\/ul>\n<h3>Why RDP<\/h3>\n<p>14 years of Make-in-India infrastructure and <strong>300,000+ devices shipped<\/strong>. Indian OEM, INR pricing, GST tax invoice, pan-India onsite engineers, GeM availability, and DPDP \/ sovereign-AI-ready deployment.<\/p>\n<h3>Buy with confidence<\/h3>\n<p>This is AI rack cooling, made to order \u2014 <strong>talk to an RDP solution architect<\/strong>, get a thermal assessment and sizing for your racks and room, and a PUE comparison <strong>before you commit.<\/strong> Request a quote to begin.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>250 kW \u00b7 Up to 400 L\/min \u00b7 Liquid-to-liquid CDU (in-rack) \u00b7 PG25 \/ treated water \u00b7 In-rack (full-height)<\/p>\n","protected":false},"featured_media":1967,"comment_status":"open","ping_status":"closed","template":"","meta":{"_yoast_wpseo_title":"","_yoast_wpseo_metadesc":"","rank_math_title":"DRACO 250 kW In-Rack CDU \u2014 250 kW, Liquid-to-liquid CDU (in-rack) | RDP GPU Mart","rank_math_description":"AI rack liquid cooling \u2014 250 kW, Liquid-to-liquid CDU (in-rack), PG25 \/ treated water. Cool dense GPU racks at full clocks, lower PUE. Make-in-India, GST invoice. Request a quote.","_hermes_jsonld":""},"product_brand":[],"product_cat":[26],"product_tag":[],"class_list":["post-1834","product","type-product","status-publish","has-post-thumbnail","product_cat-liquid-cooling-thermal","pa_form-factor-rack","pa_series-draco","first","instock","taxable","shipping-taxable","product-type-external"],"_links":{"self":[{"href":"https:\/\/rdp.in\/gpu-mart\/wp-json\/wp\/v2\/product\/1834","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/rdp.in\/gpu-mart\/wp-json\/wp\/v2\/product"}],"about":[{"href":"https:\/\/rdp.in\/gpu-mart\/wp-json\/wp\/v2\/types\/product"}],"replies":[{"embeddable":true,"href":"https:\/\/rdp.in\/gpu-mart\/wp-json\/wp\/v2\/comments?post=1834"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/rdp.in\/gpu-mart\/wp-json\/wp\/v2\/media\/1967"}],"wp:attachment":[{"href":"https:\/\/rdp.in\/gpu-mart\/wp-json\/wp\/v2\/media?parent=1834"}],"wp:term":[{"taxonomy":"product_brand","embeddable":true,"href":"https:\/\/rdp.in\/gpu-mart\/wp-json\/wp\/v2\/product_brand?post=1834"},{"taxonomy":"product_cat","embeddable":true,"href":"https:\/\/rdp.in\/gpu-mart\/wp-json\/wp\/v2\/product_cat?post=1834"},{"taxonomy":"product_tag","embeddable":true,"href":"https:\/\/rdp.in\/gpu-mart\/wp-json\/wp\/v2\/product_tag?post=1834"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}