--- title: NVIDIA's NVLink 6, Vera Rubin, and DSX platform: what... description: NVIDIA's AI Infra Summit announcements centered on efficiency framed as tokens per megawatt rather than raw throughput. The new DSX platform, tested by Lambda... canonical: https://daily.dev/posts/nvidia-s-nvlink-6-vera-rubin-and-dsx-platform-what-the-ai-infra-summit-actually-announced-b3zmwnzze twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: NVIDIA's NVLink 6, Vera Rubin, and DSX platform: what the AI Infra Summit actually announced | daily.dev og:description: NVIDIA's AI Infra Summit announcements centered on efficiency framed as tokens per megawatt rather than raw throughput. The new DSX platform, tested by Lambda... og:url: https://daily.dev/posts/nvidia-s-nvlink-6-vera-rubin-and-dsx-platform-what-the-ai-infra-summit-actually-announced-b3zmwnzze og:image: https://api.daily.dev/og/posts/b3zmwNZZE.png og:image:alt: NVIDIA's NVLink 6, Vera Rubin, and DSX platform: what the AI Infra Summit actually announced og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # NVIDIA's NVLink 6, Vera Rubin, and DSX platform: what the AI Infra Summit actually announced **[Collections](https://daily.dev/sources/collections)** · 3 min read · 1 upvotes · 0 comments ## Summary NVIDIA's AI Infra Summit announcements centered on efficiency framed as tokens per megawatt rather than raw throughput. The new DSX platform, tested by Lambda on HGX B200 servers, delivered 24% more token throughput and 23% better performance per watt, with projections of up to 40% more capacity on future Vera Rubin NVL72 systems. NVLink 6, the scale-up fabric connecting 72 Rubin GPUs, adds layered failure resiliency, including Dynamo Shadow Engine Recovery, which cut inference downtime from 283 seconds to 7.3 seconds on B200 GPUs. NVLink Fusion opens the fabric to third-party XPUs from partners like d-Matrix, AWS, Arm, Intel, and others, claiming 3x lower latency and 10x higher packet rates versus Ethernet. Power-side news included a demand-response trial with Silicon Valley Power, an 800V DC power architecture preview, and a planned 96-megawatt DSX Flex facility in Manassas, Virginia. ## Content ## The efficiency pitch: tokens per megawatt NVIDIA's framing at the AI Infra Summit was deliberate: the bottleneck for AI factories isn't GPU count, it's power. Ian Buck's presentation centered on DSX, a platform designed to squeeze more token throughput out of every megawatt rather than just stacking more hardware. The numbers Lambda put behind this are concrete. Running DSX MaxLPS on HGX B200 servers, they measured 24% more token throughput and 23% better performance per watt within the same power envelope. NVIDIA projects up to 40% more capacity for future Vera Rubin NVL72 factories using the same approach. Separately, NVIDIA's own Eos AI factory ran a real-world test of grid-aware compute: Emerald AI's Conductor software automatically throttled low-priority workloads over 200 times to participate in Silicon Valley Power's demand-response program, without interrupting inference jobs. There's also an 800V DC power architecture in preview, and a DSX Flex deployment planned for a 96-megawatt facility in Manassas, Virginia. ## Vera Rubin NVL72 benchmark results The Vera Rubin NVL72 made its MLPerf Inference v6.1 debut, and the throughput numbers are significant: - Up to 3.7x higher throughput than GB300 NVL72 on Qwen3-VL - Up to 2.5x on DeepSeek-R1 - 30x better performance per megawatt than GB300 NVL72 on SemiAnalysis AgentX agentic benchmarks The GB300 NVL72 also showed 99% scaling efficiency across a 288-GPU, four-rack configuration, and software optimizations alone drove up to 1.6x performance gains over the prior v6.0 submission. Nineteen partners submitted results on the platform, including Azure, Dell, Oracle Cloud, and CoreWeave. On the CPU side, multiple startups shared benchmark results for the new Vera CPU: Perplexity, Daytona, ClickHouse, DeepInfra, Prime Intellect, Redpanda, Starburst, and Kinetica all contributed data. Groq 3 LPX was also announced, targeting ultralow-latency inference. ## NVLink 6: resiliency at scale The Vera Rubin NVL72 connects 72 Rubin GPUs via NVLink 6, and NVIDIA published details on how the resiliency stack actually works across multiple layers: - **Physical layer:** forward error correction (FEC), proactive link recovery (PLR), and UPHY error handling - **Link layer:** lossless flow control via CBFC - **System design:** no single point of failure across the rack - **Application layer:** software recovery, including Dynamo Shadow Engine Recovery That last one is worth noting. On B200 GPUs, Dynamo Shadow Engine Recovery cuts inference downtime from 283 seconds to 7.3 seconds by keeping pre-warmed replica processes ready. NVIDIA also has prototype NCCL support for multi-node CUDA checkpointing in development. ## NVLink Fusion opens the platform to third-party chips NVLink Fusion extends this infrastructure to custom XPUs from other vendors. d-Matrix announced it will use NVLink Fusion to connect its next-generation Raptor XPUs into NVIDIA's platform, gaining access to NVLink scale-up networking, Spectrum-X scale-out networking, and the MGX rack architecture. The technical specs for NVLink Fusion: 3x lower XPU-to-XPU latency than standard Ethernet, 10x higher packet rates, and 3 TB/s per XPU of all-to-all bandwidth. Other partners in the ecosystem include AWS, Arm, Intel, Fujitsu, SiFive, Marvell, MediaTek, and Samsung, covering Arm, x86, and RISC-V CPU architectures alongside NVIDIA GPUs. The broader implication is that NVIDIA is positioning NVLink not just as an internal interconnect but as an industry fabric that third-party silicon can plug into, which changes the competitive calculus for inference chip startups considerably. ## Questions this post answers ### What is NVIDIA's Dynamo Shadow Engine Recovery and how much does it reduce inference downtime? Dynamo Shadow Engine Recovery keeps pre-warmed replica inference processes running alongside primary engines, so a failure triggers a switch to the replica instead of a full restart. On B200 GPUs this cuts inference downtime from 283 seconds to 7.3 seconds, a roughly 38x reduction, which matters for continuous inference workloads at scale. _Teams designing fault-tolerant inference clusters can follow resiliency techniques like this one on daily.dev._ ### What does NVLink Fusion let third-party chipmakers do with NVIDIA's infrastructure? NVLink Fusion lets third-party XPUs connect directly into NVIDIA's NVLink fabric instead of relying on standard Ethernet, claiming 3x lower XPU-to-XPU latency, 10x higher packet rates, and 3 TB/s of all-to-all bandwidth per XPU. d-Matrix is the first announced adopter for its Raptor XPUs, alongside partners AWS, Arm, Intel, Fujitsu, SiFive, Marvell, MediaTek, and Samsung spanning Arm, x86, and RISC-V architectures. _Engineers evaluating custom silicon versus NVIDIA's ecosystem can track interconnect news like this on daily.dev._ ### How much extra throughput does NVIDIA's DSX MaxLPS deliver on HGX B200 servers? Lambda measured 24% more token throughput and 23% better performance per watt on HGX B200 servers running DSX MaxLPS within the same power envelope, without adding more GPUs. NVIDIA separately projects up to 40% more capacity for future Vera Rubin NVL72 deployments using the same efficiency-focused approach. _daily.dev helps engineers weighing GPU efficiency claims keep up with benchmark data like this._ ## Similar posts on daily.dev - [How NVIDIA DSX MaxLPS Maximizes AI Factory Throughput and Efficiency](https://daily.dev/posts/how-nvidia-dsx-maxlps-maximizes-ai-factory-throughput-and-efficiency-8wqurs3ys) · NVIDIA Developer · 0 upvotes · 0 comments - [Maximizing AI Factory Performance per Watt with NVIDIA DSX MaxLPS](https://daily.dev/posts/maximizing-ai-factory-performance-per-watt-with-nvidia-dsx-maxlps-iamh3xeqq) · NVIDIA Developer · 0 upvotes · 0 comments - [NVIDIA AI Cloud Ecosystem Expands Worldwide to Meet Global AI Compute Demand](https://daily.dev/posts/nvidia-ai-cloud-ecosystem-expands-worldwide-to-meet-global-ai-compute-demand-j84pvvbkc) · NVIDIA · 0 upvotes · 0 comments --- Tags: [#nvidia](https://daily.dev/tags/nvidia), [#gpu](https://daily.dev/tags/gpu), [#ai-infrastructure](https://daily.dev/tags/ai-infrastructure) [View this post on daily.dev](https://daily.dev/posts/nvidia-s-nvlink-6-vera-rubin-and-dsx-platform-what-the-ai-infra-summit-actually-announced-b3zmwnzze) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"NVIDIA's NVLink 6, Vera Rubin, and DSX platform: what the AI Infra Summit actually announced","url":"https://daily.dev/posts/nvidia-s-nvlink-6-vera-rubin-and-dsx-platform-what-the-ai-infra-summit-actually-announced-b3zmwnzze","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/nvidia-s-nvlink-6-vera-rubin-and-dsx-platform-what-the-ai-infra-summit-actually-announced-b3zmwnzze"},"datePublished":"2026-09-15T20:05:14.373Z","dateModified":"2026-09-16T20:06:06.145Z","description":"NVIDIA's AI Infra Summit announcements centered on efficiency framed as tokens per megawatt rather than raw throughput. The new DSX platform, tested by Lambda...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/3c623273dad04b93c9ea7ab160fb480f?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/3c623273dad04b93c9ea7ab160fb480f?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"Collections","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"Collections","logo":"https://media.daily.dev/image/upload/s--fk_6ycEi--/f_auto,q_auto/v1780996001/logos/collections?_a=BAMAMiWQ0","url":"https://daily.dev/sources/collections"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/nvidia-s-nvlink-6-vera-rubin-and-dsx-platform-what-the-ai-infra-summit-actually-announced-b3zmwnzze","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":1},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"nvidia,gpu,ai-infrastructure","timeRequired":"PT3M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Collections","item":"https://daily.dev/sources/collections"},{"@type":"ListItem","position":3,"name":"NVIDIA's NVLink 6, Vera Rubin, and DSX platform: what the AI Infra Summit actually announced"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/nvidia-s-nvlink-6-vera-rubin-and-dsx-platform-what-the-ai-infra-summit-actually-announced-b3zmwnzze#faq","mainEntity":[{"@type":"Question","name":"What is NVIDIA's Dynamo Shadow Engine Recovery and how much does it reduce inference downtime?","acceptedAnswer":{"@type":"Answer","text":"Dynamo Shadow Engine Recovery keeps pre-warmed replica inference processes running alongside primary engines, so a failure triggers a switch to the replica instead of a full restart. On B200 GPUs this cuts inference downtime from 283 seconds to 7.3 seconds, a roughly 38x reduction, which matters for continuous inference workloads at scale. Teams designing fault-tolerant inference clusters can follow resiliency techniques like this one on daily.dev."}},{"@type":"Question","name":"What does NVLink Fusion let third-party chipmakers do with NVIDIA's infrastructure?","acceptedAnswer":{"@type":"Answer","text":"NVLink Fusion lets third-party XPUs connect directly into NVIDIA's NVLink fabric instead of relying on standard Ethernet, claiming 3x lower XPU-to-XPU latency, 10x higher packet rates, and 3 TB/s of all-to-all bandwidth per XPU. d-Matrix is the first announced adopter for its Raptor XPUs, alongside partners AWS, Arm, Intel, Fujitsu, SiFive, Marvell, MediaTek, and Samsung spanning Arm, x86, and RISC-V architectures. Engineers evaluating custom silicon versus NVIDIA's ecosystem can track interconnect news like this on daily.dev."}},{"@type":"Question","name":"How much extra throughput does NVIDIA's DSX MaxLPS deliver on HGX B200 servers?","acceptedAnswer":{"@type":"Answer","text":"Lambda measured 24% more token throughput and 23% better performance per watt on HGX B200 servers running DSX MaxLPS within the same power envelope, without adding more GPUs. NVIDIA separately projects up to 40% more capacity for future Vera Rubin NVL72 deployments using the same efficiency-focused approach. daily.dev helps engineers weighing GPU efficiency claims keep up with benchmark data like this."}}]} ```