-

Qualcomm and Cirrascale Collaborate to Advance Next-Generation, Energy-Efficient AI Inference

Highlights

  • Qualcomm Dragonfly AI200 is a purpose-built, rack-scale AI inference solution designed to deliver high performance per dollar per watt and low total cost of ownership for large language, multimodal and other AI workloads.
  • Qualcomm Dragonfly AI200 is now available for evaluation by select customers on Cirrascale’s AI Innovation Cloud, where customers can assess the platform on their own workloads and move directly into production inference deployments.
  • The collaboration combines Qualcomm Technologies' AI acceleration and rack-scale system expertise with Cirrascale's managed AI infrastructure and predictable, flat-rate cloud model.

CHICAGO--(BUSINESS WIRE)--Qualcomm Technologies, Inc. and Cirrascale Cloud Services today announced that Qualcomm Dragonfly™ AI200, a next-generation, purpose-built solution for rack-scale AI inference, is now available for evaluation by select customers through Cirrascale.

By working with Qualcomm Technologies, we can give customers evaluation access to a compelling new architecture purpose-built for the next generation of AI inference.” — Dave Driggers, CEO, Cirrascale Cloud Services

Share

As generative AI moves from model development to large-scale deployment, inference performance, power consumption and cost are becoming critical considerations for cloud providers and enterprises. Qualcomm Dragonfly AI200 is designed specifically for this challenge, combining high memory capacity, rack-scale performance and an inference-optimized software stack to help customers deploy large language, multimodal and other AI workloads with compelling performance per dollar per watt.

Through the collaboration, Cirrascale now provides select customers with an AI cloud environment in which they can evaluate and validate Qualcomm Dragonfly AI200 using their own models and workloads. The companies support platform validation, workload characterization, benchmarking, and proof-of-concept activity.

“The economics of AI are increasingly becoming the economics of inference. Our customers need efficient, scalable infrastructure that can support increasingly sophisticated models without allowing power and operating costs to become the limiting factor. By working with Qualcomm Technologies, we can give customers evaluation access to a compelling new architecture purpose-built for the next generation of AI inference.”

— Dave Driggers, CEO, Cirrascale Cloud Services

Qualcomm Dragonfly AI200 supports 768 GB of LPDDR memory per card, providing the memory capacity and flexibility required for large-scale AI inference. It is architected to support inference for next-generation foundation models at trillion-parameter scale, delivering the performance and efficiency required for advanced AI applications. The rack-level solution also combines direct liquid cooling, PCIe scale-up, Ethernet scale-out and confidential computing, and is supported by Qualcomm AI Management Suite and ecosystem support for leading AI frameworks.

Rather than relying solely on general-purpose infrastructure, select customers can now use Cirrascale’s environment to assess a platform designed specifically for inference. Cirrascale brings experience operating dedicated AI cloud infrastructure, managed services and a transparent, flat-rate commercial model without ingress or egress fees.

“AI inference is becoming one of the largest and most important computing workloads in the data center, and the industry needs a more efficient approach. Qualcomm AI200 brings our leadership in high-performance, low-power AI computing to rack-scale infrastructure, with an architecture designed around the performance, memory and cost requirements of inference. Our work with Cirrascale gives customers a direct way to evaluate this technology on their own workloads and experience the resulting data center economics.”

— Tony Pialis, EVP and GM, Qualcomm Datacenter

The companies anticipate this collaboration establishing a foundation for continued work across Qualcomm Technologies’ multi-generation data center AI inference roadmap.

Availability

Qualcomm Dragonfly AI200 is available now for evaluation by select customers through Cirrascale. A demonstration will also be available at the SC26 conference in Chicago from November 17-18 in Cirrascale’s booth #1046.

Additionally, Rashid Attar, Qualcomm Technologies SVP of Engineering, will join David Driggers, Cirrascale CEO, Pavan Balaji, Meta Research Scientist and Technical Lead, and Greg Yeric, VP of Portfolio, Compute Systems Scaling, Imec, for a TechArena breakfast panel on near-memory compute and the future of AI infrastructure on Wednesday, November 18 from 8:30 am – 10 am. Register for the panel here.

About Cirrascale Cloud Services

Cirrascale Cloud Services provides cloud infrastructure purpose-built for AI workloads. Its AI Innovation Cloud supports generative AI workloads from model development through real-time inference, with dedicated infrastructure, managed services and transparent flat-rate billing without ingress or egress fees. For more information, visit www.cirrascale.com.

About Qualcomm

Qualcomm is a global computing leader at the center of the AI era, enabling intelligence to scale from the most personal devices to large‑scale infrastructure. Building on more than four decades of innovation, we develop platforms and solutions that bring together advanced AI, high‑performance, low-power computing and industry‑leading connectivity—powering products and services used around the world. At Qualcomm, we are engineering human progress.

Qualcomm Incorporated includes our licensing business, QTL, and the vast majority of our patent portfolio. Qualcomm Technologies, Inc., a subsidiary of Qualcomm Incorporated, operates, along with its subsidiaries, substantially all of our engineering and research and development functions and substantially all of our products and services businesses, including our QCT semiconductor business. Snapdragon and Qualcomm branded products are products of Qualcomm Technologies, Inc. and/or its subsidiaries. Qualcomm patents are licensed by Qualcomm Incorporated. Qualcomm, Snapdragon, Qualcomm Dragonwing and Qualcomm Dragonfly are trademarks or registered trademarks of Qualcomm Incorporated.

Qualcomm and Qualcomm Dragonfly are trademarks or registered trademarks of Qualcomm Incorporated.

Cirrascale Cloud Services


Release Versions

More News From Cirrascale Cloud Services

Cirrascale Cloud Services Launches Production Release of the Cirrascale Inference Platform, Delivering a Complete Enterprise AI Inference Stack

SANTA CLARA, Calif.--(BUSINESS WIRE)--AI Infra Summit – Cirrascale Cloud Services, the expert neocloud built for Private AI, today announced the production release of the Cirrascale Inference Platform, a complete software stack for enterprise-grade AI inference. From a single serverless platform, enterprises can run open-source models, their own private models, and closed model ecosystems, including Google Gemini delivered on premises through Google Distributed Cloud and operated by Cirrascale....

Cirrascale Advances Open AI Infrastructure with AMD Helios Rackscale Solution and AMD Instinct™ MI400 Series GPUs

SAN DIEGO--(BUSINESS WIRE)--Cirrascale Cloud Services, the expert neocloud built for Private AI, today announced support for the AMD Helios rackscale solution and AMD Instinct™ MI400 Series GPUs across its AI innovation cloud. The addition brings AMD rack-scale AI infrastructure, powered by AMD Instinct™ MI455X GPUs, to Cirrascale customers running large-scale inference, frontier-model training, and fine-tuning, and it extends Cirrascale's open, multi-vendor approach to accelerated computing. A...

Cirrascale Cloud Services Adds Tenstorrent Galaxy Blackhole to Its AI Innovation Cloud

SAN DIEGO--(BUSINESS WIRE)--Cirrascale Cloud Services, the expert neocloud built for Private AI, today announced the addition of Tenstorrent Galaxy Blackhole servers to its AI Innovation Cloud. The integration marks Tenstorrent's entry into broad commercial deployment and expands Cirrascale's portfolio with hardware built specifically for the demands of real-world AI. Tenstorrent Galaxy is engineered around the metrics that matter most in production AI environments: cost per token, latency per...
Back to Newsroom