Puget Systems Makes its Debut at CVPR 2024 with Demonstrations of its “On-Premise” Generative AI and Machine Learning Custom Server
Puget Systems to Demonstrate its Specialized AI Training and Inference Server Running Complex, GPU-Intensive, and Local StreamDiffusion Generative AI Pipeline
Auburn, WA (June 18, 2024) – Puget Systems (www.pugetsystems.com) today announced it will make its debut at the CVPR (Computer Vision and Pattern Recognition) Conference in Seattle, WA later this week to demonstrate its newest custom Generative AI and Machine Learning server. The CVPR Conference is the preeminent event for research and development in computer vision, artificial intelligence (AI), machine learning (ML), augmented, virtual and mixed reality (AR/VR/MR), and deep learning.
In its booth #2113 in the Seattle Convention Center, the team from Puget Systems will demonstrate its latest specialized AI Training and Inference server running a sophisticated, GPU-intensive, real-time AI image generation solution that uses a StreamDiffusion pipeline. The demonstration is run locally on the Puget Systems server to showcase how these complex, hardware-intensive workflows – which require powerful GPUs such as the NVIDIA GeForce RTX 4090 and NVIDIA RTX 6000 Ada to generate high-quality imagery with smooth frame rates – are possible using Puget Systems custom, localized hardware.
Attendees at the booth will see how the Puget Systems Generative AI and Machine Learning Server can pass a source image into a Stream Diffusion operator in TouchDesignerwith a GUI to control the Stream Diffusion parameters, such as the Acceleration Library, Resolution, Steps, and Prompt. Additionally, various input methods can be selected in the GUI including Webcam, Visual Noise, Photoshop (for live AI painting), and a mouse pointer for physical fluid simulation. The interpretation of the input image then creates an AI-generated output image in real-time at high frame rates.
The Puget Systems AI Training and Inference Server: Flexible, Scalable, Powerful
The Puget Systems AI Training and Inference Servers are rackmount workstations specifically designed for GPU-intensive Generative AI workflows, much like the StreamDiffusion demo shown in the booth at CVPR.
The newest Puget Systems AI Training and Inference Servers offer AMD’s EYPC line of processors, which are designed for demanding server workloads, offering up to 128 cores with support for 12 DDR5 memory channels and 128 PCIe Gen 5 lanes. This Server uses a pair of those CPUs to enable up to eight dual-width GPUs in a 4U rackmount chassis, and several hot-swap drive bays are easily accessible on the front, along with a pair of USB ports.
With support for up to eight NVIDIA GPUs with up to 752GB of total VRAM, this server is perfect for machine learning, AI, and rendering workloads. Additionally, for enterprise or data center customers, the Puget Systems AI Training and Inference Server also offers support for the NVIDIA H100 NVL Tensor Core GPU. The H100 NVL is the most optimized platform for LLM Inferences with its high compute density, high memory bandwidth, high energy efficiency, and unique NVLink architecture. It also delivers unprecedented acceleration to power the world’s highest-performing elastic data centers for AI, data analytics, and high-performance computing (HPC) applications.
For more information, please visit here.
Pricing and Availability
Puget Systems custom AI Training and Inference servers are available for configuration for a wide range of Generative AI applications. To learn more, please visit here. To learn more about Puget Systems Canadian consulting and sales operations, please visit here.
About Puget Systems
Puget Systems is based in the Seattle suburb of Auburn, WA, and specializes in high-performance custom-built computers. We emphasize customization with a laser focus on understanding each customer’s specific workflow and offer personal consulting and support that we believe is becoming quite rare in the industry. Our goal is to provide each client with the best possible computer for their needs and budget. For more information or to see how Puget Systems can design a system specifically tailored to the work that you do, please visit www.pugetsystems.com.