Vultr maximizes AI throughput with AMD Instinct MI355X GPUs, leveraging advanced architecture and optimized design to provide exceptional performance for demanding AI workloads.
Vultr, the world’s largest privately-held cloud infrastructure provider, has announced that it is among the inaugural cloud platforms to offer the new AMD Instinct™ MI355X GPU. As a top-tier sponsor of the AMD Advancing AI initiative, Vultr has opened pre-orders for early access to the MI355X GPUs, which will be available globally starting in Q3. This strategic move aims to empower customers with cutting-edge tools to accelerate a wide spectrum of AI workloads.
Powered by AMD’s 4th Gen CDNA architecture, the Instinct MI355X GPU delivers outstanding computational performance and energy efficiency across diverse use cases—from AI model training and inference to high-performance scientific computing. With 288 GB of HBM3E memory, 8 TB/s of memory bandwidth, and expanded datatype support including FP6 and FP4, the MI355X is engineered to meet the demands of both AI and HPC (high-performance computing) applications.
Designed for high-density deployments, the platform also offers direct liquid cooling (DLC) options. This advanced cooling solution enhances thermal performance and enables higher compute density per rack, ideal for organizations scaling their infrastructure. These hardware features are further augmented by updates to AMD’s ROCm™ software stack, which boosts compatibility with major AI frameworks, reduces latency, and ensures maximum throughput for both training and inference tasks.
Also Read: DigitalOcean & AMD Partner to Boost AI with Cloud GPUs
“AMD is the trusted AI solutions provider of choice, enabling customers to tackle the most ambitious AI initiatives, from building large-scale AI cloud deployments to accelerating AI-powered scientific discovery,” said Negin Oliver, corporate vice president of business development, Data Center GPU Business, AMD. “AMD Instinct MI350 series GPUs paired with AMD ROCm software provide the performance, flexibility, and security needed to deliver tailored AI solutions that meet the diverse demands of the modern AI landscape.”
The MI355X GPUs further expand Vultr’s comprehensive suite of AMD-based offerings, which already includes AMD EPYC™ 9004 and 7003 Series CPUs, along with AMD Instinct MI325X and MI300X GPUs. When deployed alongside AMD EPYC™ 4005 Series CPUs, users benefit from an optimized, full-stack solution—from compute to acceleration—for seamless integration and maximum performance.
“AMD MI355X GPUs are designed to meet the diverse and complex demands of today’s AI workloads, delivering exceptional value and flexibility,” said J.J. Kardwell, CEO of Vultr. “As AI development continues to accelerate, the scalability, security, and efficiency these GPUs deliver are more essential than ever. We are proud to be among the first cloud providers worldwide to offer AMD MI355X GPUs, empowering our customers with next-generation AI infrastructure.”
