Announcement Webinar Podcast GTC 2026 CoreWeave Forge is here: connect your AI loop and compound every improvement. Read more ← Main menu CoreWeave Cloud Main menu The CoreWeave Cloud Platform CoreWeave Cloud Platform → The AI cloud purpose-built for…
Announcement
Webinar
Podcast
GTC 2026
CoreWeave Forge is here: connect your AI loop and compound every improvement. Read more
← Main menu
CoreWeave Cloud
Main menu
The CoreWeave Cloud Platform
CoreWeave Cloud Platform →
The AI cloud purpose-built for training and serving models at scale
Why CoreWeave
Why CoreWeave
What sets our AI cloud apart
CoreWeave ARENA
Benchmark and showcase AI workloads on CoreWeave
CoreWeave Partner Network
Integrations, solutions, and expertise to accelerate production AI
Global AI data centers
Purpose-built AI data centers around the world
About us
Our company, mission, and leadership
CoreWeave Direct-to-Expert
Work directly with the engineers behind the platform
Trust Center
Security on every layer of your compute experience
Programs and Services
CoreWeave Ventures
Backing the next generation of AI companies
Physical AI Field Engineering
Embedded engineers, building physical AI with your team
Academic Research
Supporting researchers with access to GPU cloud and AI tooling
Zero Egress Migration (0EM)
Move your data to CoreWeave with zero egress fees
Infrastructure
Main menu
Infrastructure
Compute
GPU compute
The latest NVIDIA GPUs at cluster scale
NVIDIA Vera Rubin
NVIDIA Blackwell
NVIDIA Hopper
CPU compute
General-purpose compute for supporting workloads
Bare Metal Compute
Direct hardware access, no virtualization overhead
Networking
Networking
High-bandwidth, low-latency fabric for AI clusters
Storage
AI Object Storage
Object storage tuned for AI training and inference
Dedicated Storage
Dedicated VAST clusters for demanding data needs
Zero Egress Migration (0EM)
Move your data to CoreWeave with zero egress fees
Infrastructure Control
CoreWeave Kubernetes Service (CKS)
Managed Kubernetes built for AI workloads
Mission Control
Mission Control
Fleet health, monitoring, and control in one place
Fleet Lifecycle Controller
Automated lifecycle management for your fleet
Node Lifecycle Controller
Keep every node healthy and current
Observability
Metrics, logs, and traces across your clusters
Security
Protection built into every layer of the stack
Tensorizer
Load models faster with optimized serialization
Infrastructure Pricing ›
Log in
CoreWeave Forge
Main menu
CoreWeave Forge
CoreWeave Forge →
Models, agents, training, and inference
Training
Weights & Biases Models
Track, compare, and reproduce every experiment
Serverless SFT
Fine-tune open models with nothing to provision
Serverless RL
Managed reinforcement learning, no stack to operate
Model Distillation
Preview
A smaller model, scored against the one you run
Inference
Serverless Inference
Open models on one API, billed per token
Dedicated Inference
Your weights on GPUs you choose, managed for you
Agent Development
Agent Lens
Preview
Observability that turns agent traces into fixes
Sandboxes
Isolated execution for agent and RL code
Tools
ARIA
A research agent that analyzes your runs
Registry
System of record for models, agents, and datasets
Notebooks
Reactive Python notebooks, connected to your runs
Forge Pricing ›
Log in
Solutions
Main menu
Solutions by use case
Solutions by use case
Training
AI model training
Train large-scale AI models with purpose-built GPU infrastructure
Reinforcement learning
Post-train and optimize agents using reinforcement learning
Agentic AI and Inference
Agentic AI
Close the loop between training and inference to improve agent reliability
AI inference
Run low-latency AI inference with high-performance compute
Agent development
Develop, evaluate, and refine AI agents with confidence
Specialized Workloads
VFX rendering
Accelerate VFX and rendering with scalable GPU power
Solutions by industry
Federal
Secure AI infrastructure for government missions
Media and entertainment
Rendering and AI pipelines for studios
Physical AI
Compute for robotics and real-world AI systems
Resources
Main menu
Resources
Learn
Resource center
Explore whitepapers, briefs, videos and more
Customer stories
See how leading teams build and scale with CoreWeave
Webinars and events
Join live events and watch on-demand sessions
Blog
Insights on AI cloud, infrastructure, and innovation
Topics
Explore foundational concepts in AI, cloud infrastructure, and emerging technologies
Newsroom
Company news, announcements, and press
For Developers
Builder resource center
Guides, samples, and tools for builders
GitHub library
Open-source repos, SDKs, and examples
Support
Documentation
Technical documentation and implementation guides
Status
Real-time platform availability and system updates
Direct-to-Expert
Work directly with the engineers behind the platform
Log in
Main menu
Log in
CoreWeave Forge
Models, agents, training, and inference
CoreWeave Infrastructure
AI Cloud compute, storage, and observability
|
Sign up
Contact us
Contact us

Clear


Published on
September 30, 2026

3
min read
CoreWeave Delivers NVIDIA Vera Rubin NVL72 Performance at Production Scale, Starting With Cognition
CoreWeave maintains industry-leading AI cloud performance across multiple compute generations with its software platform
No items found.
Copied

SAN FRANCISCO — Sept. 30, 2026 — CoreWeave
Inc. (Nasdaq: CRWV), The Essential Cloud for AI™, today announced the availability of NVIDIA Vera Rubin NVL72
on CoreWeave, with Cognition as the first customer anywhere running production workloads on the system. Customers, like Cognition, run the system under the same operating model and tooling as their existing NVIDIA GB200 NVL72 and GB300 NVL72 fleets, with performance engineering from CoreWeave’s team. The news was shared during Fully Connected
, CoreWeave’s AI cloud conference, which brings together more than 4,500 customers, partners, developers and AI leaders to share how they are building and running AI in production.
“Bringing up NVIDIA Vera Rubin NVL72 so quickly, and having a customer already seeing performance gains within days, is the payoff from years of engineering our platform across GPU generations,” said Chen Goldberg, executive vice president of product & engineering at CoreWeave. “With customers like Cognition, that investment shows up in the ability to get production workloads running within days. When it comes to agentic tasks, long contexts, repeated model calls and thousands of concurrent tasks put pressure on the entire platform. Our job is to make compute, networking and software work as a single system, so customers can build increasingly complex agents without taking on the infrastructure complexity themselves.”
Cognition is the first customer in production with Vera Rubin NVL72
Cognition, the applied AI lab behind Devin, runs training, reinforcement learning and production inference for Devin on CoreWeave. The company scaled from bridge capacity to thousands of GPUs for training and inference in less than nine months. Cognition worked with CoreWeave to stand up a Vera Rubin NVL72 cluster in early September, and Cognition’s own engineers ran the first customer-executed Vera Rubin inference benchmark, measured against a GB200 NVL72 cluster baseline.
“Agentic coding is an unforgiving workload that requires long contexts, high concurrency and rapid reasoning.” said Silas Alberti, SVP research & founding team at Cognition. “By deploying the NVIDIA Vera Rubin NVL72 on CoreWeave, our engineers are seeing up to a 4.8 times increase in total token throughput for SWE-2 inference workloads. For an agentic workload where every step waits on the last one, that compounds into real work Devin gets done. CoreWeave continues to deliver the bleeding-edge rack-scale acceleration we need to push the boundaries of AI.”
Cognition’s engineers benchmarked Vera Rubin
In independent benchmarks run on CoreWeave Cloud, Cognition measured a 4.8 times increase in total token throughput for its SWE-2 inference workloads on NVIDIA Vera Rubin NVL72 compared to a GB200 NVL72 baseline. Additionally, the team recorded a 3.8 times boost in output token throughput for reinforcement learning workloads. For Cognition, that translates to more concurrent Devin sessions per GPU, drastically accelerated research loops and lower cost per session, with no loss in generation speed.
Proven across every NVIDIA generation
The relationship between CoreWeave and NVIDIA dates to 2017, beginning with the NVIDIA Volta generation, which is still in commercial service today on CoreWeave Cloud, demonstrating the long useful life of NVIDIA compute and the value CoreWeave’s platform can continue to draw from it. CoreWeave’s full-stack software platform—including CoreWeave Kubernetes Service, SUNK, CoreWeave Mission Control®, CoreWeave Sandboxes and serverless inference—gives customers a consistent way to deploy and manage workloads across GPU generations. Customers can match each workload to appropriate capacity, keep using existing infrastructure as needs evolve and adopt new NVIDIA architectures through a familiar operating environment.
“CoreWeave has consistently demonstrated the infrastructure expertise required to bring each new generation of NVIDIA accelerated computing into production,” said Ian Buck, vice president of Hyperscale and High-Performance Computing at NVIDIA. “Its full-stack expertise across multiple generations of NVIDIA infrastructure is helping AI innovators like Cognition quickly put NVIDIA Vera Rubin NVL72 to work on demanding production workloads.”
CoreWeave, in collaboration with Dell Technologies, was among the first cloud
providers
to deploy Dell PowerRack systems featuring NVIDIA GB200 and GB300 NVL72, and is one of the first to deploy NVIDIA Vera Rubin. CoreWeave has also published the industry’s first measured silicon performance numbers on the platform, showing 10 times the token throughput per megawatt
over NVIDIA GB200 NVL72 on the DeepSeek R1 reasoning model at matched interactivity.
CoreWeave consistently delivers industry-leading performance, demonstrated by record-breaking MLPerf benchmark results in inference
and training
and its position as the only AI cloud to earn the top Platinum
ranking in SemiAnalysis ClusterMAX™ three times in a row.
About CoreWeave
CoreWeave is The Essential Cloud for AI™. Built for pioneers by pioneers, CoreWeave delivers a platform of technology, tools, and teams that enables innovators to move at the pace of innovation, building and scaling AI with confidence. Trusted by leading AI labs, startups, and global enterprises, CoreWeave serves as a force multiplier by combining superior infrastructure performance with deep technical expertise to accelerate breakthroughs. Established in 2017, CoreWeave completed its public listing on Nasdaq (CRWV) in March 2025. Learn more at www.coreweave.com
.
Share this article:
Copied
Media Contacts
CoreWeave Media
[email protected]
More press releases



CoreWeave Launches the CoreWeave Zero Trust AI Framework, Keeping Customers in Control of Access to Their Models, Data and Runtime Environments
Six layers of customer-controlled security, from encryption keys to runtime, designed to keep CoreWeave out of the customer's trust chain
4
min read


CoreWeave Unveils CoreWeave Physical AI Launchables, Taking the Setup Work Out of Robotics and AV Development
Engineers get tested configurations for the software they already use, so time goes into the work instead of the plumbing
4
min read

.jpg)
CoreWeave Enters India, Expanding AI Cloud Platform With AdaniConneX
CoreWeave enters India with AdaniConneX, planning a 240 MW deployment in Navi Mumbai to bring its purpose-built AI Cloud closer to customers.
3
min read


Ennoble Care selects CoreWeave to power AI inference across its home-based care network
The home-based care provider and accountable care organization will run its inference workloads on NVIDIA RTX PRO 6000 GPUs deployed through CoreWeave Kubernetes Service
3
min read


CoreWeave Partner Network Accelerates the Path to AI Innovation
Brings validated partner integrations into one curated place Spans the AI loop, anchored by years-deep collaborations with Reflection, VAST Data, ClickHouse, CrowdStrike and more
min read


CoreWeave to Offer NVIDIA Vera, the First CPU Built for AI agents
CoreWeave expands compute portfolio to meet the needs of AI workloads.
min read


CoreWeave Forge Launches, Turning the AI Loop Production Run Into a Better Model and Agent
One connected environment for training, inference, evaluation and agent development, open across models, frameworks and other clouds, so every version ships sooner and performs better than the last
4
min read


CoreWeave Becomes the Only Provider to Earn SemiAnalysis' Platinum ClusterMAX™ Rating Three Consecutive Times
Repeat recognition as the only Platinum AI cloud in every ClusterMAX evaluation underscores CoreWeave's sustained leadership
2
min read


Harell Data Selects CoreWeave to Power Its Secure Platform for AI Model Training
Multi-year agreement gives Harell Data the AI cloud to train and fine-tune proprietary biotech datasets as it scales its research platform
3
min read


CoreWeave Brings Up Multi-Rack NVIDIA Vera Rubin NVL72 Cluster
New capabilities across compute, storage, and networking keep customers productive and accelerate the AI loop
4
min read

Also of interest
Products
Solutions
Resources
© CoreWeave.
290 W Mt Pleasant Ave
Suite 4100
Livingston, NJ 07039

No items found.

Heading
5 min read
Learn more
We use cookies to enhance your browsing experience and analyze site traffic. By continuing to use our site, you consent to our use of cookies.
Manage My Cookies Settings Learn More

Privacy Preference Center
When you visit any website, it may store or retrieve information on your browser, mostly in the form of cookies. This information might be about you, your preferences, or your device, and is mostly used to make the site work as you expect. The information does not usually identify you directly, but it can give you a more personalized web experience. Because we respect your right to privacy, you can choose not to allow some types of cookies. Click on the different category headings to learn more and change our default settings. Blocking some types of cookies may impact your experience of the site and the services we are able to offer.
More information
Allow All
Manage Consent Preferences
Functional Cookies
Functional Cookies
These cookies enable the website to provide enhanced functionality and personalisation. They may be set by us or by third party providers whose services we have added to our pages. If you do not allow these cookies then some or all of these services may not function properly.
Performance Cookies
Performance Cookies
These cookies allow us to count visits and traffic sources so we can measure and improve the performance of our site. They help us to know which pages are the most and least popular and see how visitors move around the site. All information these cookies collect is aggregated and therefore anonymous. If you do not allow these cookies we will not know when you have visited our site, and will not be able to monitor its performance.
Targeting Cookies
Targeting Cookies
These cookies may be set through our site by our advertising partners. They may be used by those companies to build a profile of your interests and show you relevant adverts on other sites. They do not store directly personal information, but are based on uniquely identifying your browser and internet device. If you do not allow these cookies, you will experience less targeted advertising.
Strictly Necessary Cookies
Always Active
These cookies are necessary for the website to function and cannot be switched off in our systems. They are usually only set in response to actions made by you which amount to a request for services, such as setting your privacy preferences, logging in or filling in forms. You can set your browser to block or alert you about these cookies, but some parts of the site will not then work. These cookies do not store any personally identifiable information.
Back Button
Cookie List
Search Icon
Filter Icon
Clear
Apply Cancel
Consent Leg.Interest
checkbox label label
checkbox label label
checkbox label label
Reject All Confirm My Choices
