QuTScloud

QuTScloud is the operating system for QNAP Cloud NAS virtual appliances. With the possibility of on-premises and cloud deployment, QuTScloud enables optimized cloud data usage and flexible resource allocation at a predictable monthly cost.

System
Applications

QES

QES is the operating system for dual-controller QNAP NAS models. With FreeBSD and ZFS, QES is flash-optimized, capable of driving outstanding performance for all-flash storage arrays.

System
Product
Resources

QNE Network

QNE Network is the operating system for QuCPE, QNAP's universal customer premises equipment series. Run virtual network functions, freely configure software-defined networks, and enjoy benefits such as lowered costs and reduced management efforts.

System
Applications

QSS

QNAP Switch System (QSS) is the configuration interface for QNAP's managed switch series. Enable management functions such as link aggregation, VLAN, and RSTP, to take care of your network topology with ease.

System

QuRouter

QNAP’s QuRouter OS simplifies managing high-speed and high-coverage LAN/WAN. With NAT, VPN, security, and QuWAN SD-WAN, network management is made easier and remote connections more secure.

System
Applications

QVR Surveillancee

QVR Surveillance is QNAP’s network video recorder software solution. It offers subscription-based QVR Elite and perpetual QVR Pro, and can be used with a series of apps, such as face recognition and door access control for a wider range of scenarios.

System
Applications
Resources

QVR Face

QVR Face is a smart facial recognition solution featuring real-time live streaming video analytics from connected cameras. It can be integrated into multiple scenarios to provide intelligent attendance management, door access control management, VIP welcome systems and smart retail services.

System
Applications
Resources

KoiMeeter

QNAP smart video solutions provides integrated intelligent packages such as video conferencing and smart retail, boosting productivity for individuals and businesses.

Video Conferencing
Smart Retail

Mustang-V100 (VPU)
Intel® Vision Accelerator Design with Intel® Movidius™ VPU

mustang-v100

As QNAP NAS evolves to support a wider range of applications (including surveillance, virtualization, and AI) you not only need more storage space on your NAS, but also require the NAS to have greater power to optimize targeted workloads. The Mustang-V100 is a PCIe-based accelerator card using an Intel® Movidius™ VPU that drives the demanding workloads of modern computer vision and AI applications. It can be installed in a PC or compatible QNAP NAS to boost performance as a perfect choice for AI deep learning inference workloads. >> Difference between Mustang-F100 and Mustang-V100.

  • Half-height, half-length, single-slot compact size.
  • Low power consumption, approximate 2.5W for each Intel® Movidius™ Myriad™ X VPU.
  • Supported OpenVINO™ toolkit, AI edge computing ready device.
  • Eight Intel® Movidius™ Myriad™ X VPU can execute eight topologies simultaneously.

Logo_Intel-Movidius

Available Models

Mustang-V100-MX8-R11

Computing Accelerator Card with 8 x Movidius Myriad X MA2485 VPU, PCIe Gen2 x4 interface, RoHS, Rev 1.1

Mustang-V100-MX8-R10

Computing Accelerator Card with 8 x Movidius Myriad X MA2485 VPU, PCIe Gen2 x4 interface, RoHS, Rev 1.0

OpenVINO™ toolkit

OpenVINO™ toolkit is based on convolutional neural networks (CNN), the toolkit extends workloads across Intel® hardware and maximizes performance.

It can optimize pre-trained deep learning model such as Caffe, MXNET, Tensorflow into IR binary file then execute the inference engine across Intel®-hardware heterogeneously such as CPU, GPU, Intel® Movidius™ Neural Compute Stick, and FPGA.

Get deep learning acceleration on Intel-based Server/PC

You can insert the Mustang-V100 into a PC/workstation running Linux® (Ubuntu®) to acquire computational acceleration for optimal application performance such as deep learning inference, video streaming, and data center. As an ideal acceleration solution for real-time AI inference, the Mustang-V100 can also work with Intel® OpenVINO™ toolkit to optimize inference workloads for image classification and computer vision.

  • Operating Systems
    Ubuntu 16.04.3 LTS 64-bit, CentOS 7.4 64-bit, Windows 10 (More OS are coming soon)
  • OpenVINO™ Toolkit
    • Intel® Deep Learning Deployment Toolkit
      • - Model Optimizer
      • - Inference Engine
    • Optimized computer vision libraries
    • Intel® Media SDK
      *OpenCL™ graphics drivers and runtimes.
    • Current Supported Topologies: AlexNet, GoogleNet V1, Yolo Tiny V1 & V2, Yolo V2, SSD300, ResNet-18, Faster-RCNN. (more variants are coming soon)
  • High flexibility, Mustang-V100-MX8 develop on OpenVINO™ toolkit structure which allows trained data such as Caffe, TensorFlow, and MXNet to execute on it after convert to optimized IR.

*OpenCL™ is the trademark of Apple Inc. used by permission by Khronos

QNAP NAS as an Inference Server

OpenVINO™ toolkit extends workloads across Intel® hardware (including accelerators) and maximizes performance. When used with QNAP’s OpenVINO™ Workflow Consolidation Tool, the Intel®-based QNAP NAS presents an ideal Inference Server that assists organizations in quickly building an inference system. Providing a model optimizer and inference engine, the OpenVINO™ toolkit is easy to use and flexible for high-performance, low-latency computer vision that improves deep learning inference. AI developers can deploy trained models on a QNAP NAS for inference, and install the Mustang-V100 to achieve optimal performance for running inference.

Note:
1. QTS 4.4.0~4.4.3 and OWCT v1.1.0 are required for the QNAP NAS.
2. Check Compatibility List for supported models.
3. Installing “Mustang Card User Driver” for Mustang-V100-R10 in the QTS App Center is required. Mustang-V100-R11 (or later) is not supported.

Easy-to-manage Inference Engine with QNAP OWCT

  • Upload a video file

  • Download inference result

Applications

  • Machine Vision

  • Smart Retail

  • Surveillance

  • Medical Diagnostics

Dimensions

(Unit: mm)

Note:
Up to 16 cards can be supported with operating systems other than QTS; QNAP TS-2888X NAS supports up to 8 cards. Please assign a card ID number (from 0 to 15) to the Mustang-V100 by using rotary switch manually. The card ID number assigned here will be shown on the LED display of the card after power-up.

Choose specification

      Show more Less

      Choose Your Country or Region

      open menu
      back to top