• Expanding our Agentic Inference Cloud: Introducing GPU Droplets Powered by AMD Instinct™ MI350X GPUs ByWaverly Swinton Published:February 19, 2026 2 min read As our Agentic Inference Cloud continues to grow, we’re excited to announce the availability of new, high-performanceGPU Dropletspowered byAMD Instinct™ MI350X GPUs. • By integrating these cutting-edge GPUs with our platform, we’re continuing to deliver the power and scale that leading AI-native companies and builders need to run their most complex inference workloads. • Optimizing production inference with AMD Instinct™ MI350X The AMD Instinct™ MI350X Series sets a new standard for generative AI and high-performance computing (HPC). • Built on the AMD CDNA™ 4 architecture, these GPUs are designed for the most demanding tasks: training massive models, high-speed inference, and complex scientific simulations. • The capabilities of the GPUs allow optimization for the compute bound prefill phase, while enabling high-performance inference at low latency and high token generation throughput. • This provides the ability to load large models and larger context windows, leading to supporting a higher inference request density per GPU.

Article Summaries:

  • As our Agentic Inference Cloud continues to grow, we’re excited to announce the availability of new, high-performance GPU Droplets powered by AMD Instinct™ MI350X GPUs. By integrating these cutting-edge GPUs with our platform, we’re continuing to deliver the power and scale that leading AI-native companies and builders need to run their most complex inference workloads. The AMD Instinct™ MI350X Series sets a new standard for generative AI and high-performance computing (HPC). Built on the AMD CDNA™ 4 architecture, these GPUs are designed for the most demanding tasks: training massive models, h

Sources: