GPGPU
あなたの製品を検索

あなたの製品を検索

  • QuantaGrid D75T-7U

    Accelerated Performance for Modern AI-HPC Workloads

    • Powered by dual AMD EPYC™ 9005 Series processors and 8x AMD Instinct™ MI350X/MI325X GPUs
    • UBB architecture to support AI & HPC workloads
    • Up to 24 DIMMs for up to 3 TB of memory (with AMD EPYC™ 9005 Series processors)
    • 18x SFF All-NVMe drive bays for GPU Direct Storage and boot drive
    • 8x HHHL SW PCIe Gen5 x16 slots
    • Modularized design for easy serviceability
  • QuantaGrid D75F-7U

    Seamless Data Processing and High-Performance AI at Scale

    • Powered by dual 5th/4th Gen Intel® Xeon® Scalable processors and 8x NVIDIA HGX™ H200 GPUs.
    • 18x SFF All-NVMe drive bays for GPU Direct Storage and boot drive
    • 2x NVIDIA® BlueField®-3 DPUs to minimize the bottleneck and empowering the performance for the most complex AI-HPC workloads
    • 8x HHHL SW PCIe Gen 5 x16 slots for 1:1 GPU-Direct RDMA
    • Modularized system design for optimal flexibility and easy serviceability
    • System optimized for generative AI, LLM, and HPC workloads
  • QuantaGrid S74G-2U

    Breakthrough accelerated performance for giant-scale AI-HPC applications

    • Introducing the first gen NVIDIA® MGX™ architecture with modular infrastructure
    • Powered by NVIDIA® Grace™ Hopper™ Superchip
    • Coherent memory between CPU and GPU with NVLink®- C2C interconnect
    • Optimized for memory intensive inference and HPC performance
    • arm SystemReady
  • QuantaGrid-D43N-3U

    Optimized Accelerated Server

    • Flexible acceleration card configuration optimized for both compute and graphic intensive workloads
    • Up to 128 CPU cores with 8TB memory capacity to feed high throughput accelerator cards
    • Up to 2x HDR/200GbE networking to cluster computing
    • Easy maintenance design for minimum downtime
  • QuantaGrid D74A-7U

    Accelerated Parallel Computing Performance for the Most Extreme AI-HPC Workloads

    • Multiple-GPUs Server for HPC / AI Training ( e.g LLMs / NLP ).
    • Powered by 2x 4th AMD EPYC9004 Processors and Compatible with Next-Gen AMD EPYC™ Processor in the future.
    • Introducing NVIDIA HGX Architecture and Flexible with 8x NVIDIA H100 GPUs or 8x AMD MI300X GPUs.
    • 18x SFF All-NVMe Drive Bays for GPUDirect Storage and Boot Drive.
    • 10x OCP NIC 3.0 TSFF for GPUDirect RDMA.
    • Modularized Design for Easy Serviceability.
  • QuantaGrid D54U-3U

    Endless Flexibility for Diverse Applications​

    • Powered by 5th/4th Gen Intel® Xeon® Scalable Processor
    • Powered by NVIDIA® GPUs
    • PCle 5.0 & DDR5 platform ready
    • Up to 4x DW accelerator or 8x SW accelerator
    • Support active type and passive type accelerator
    • Up to 10x PCIe 5.0 NVMe drive to speed up data-loading
    • PCle 5.0 400Gb Networking for Scale-out
    • Enhanced serviceability with tool-less, hot-plug designs
of
2