expert in AIoT system solution

Container × GPU × AI Pod Platform

AI Compute Platform - VIDAware Containerization

An Elastic Runtime and Real-Time Scheduling Hub Built Around AI Service Units (Pods)

Built around an AI containerized compute platform, each AI model, video analytics task, and event inference service is packaged as an independent AI service unit (Pod). According to real-time requirements across city sites, workloads can be automatically assigned to different GPU compute nodes, enabling real-time scaling, uninterrupted operation, and cross-node fault tolerance for city-scale AI computing.

Distributed Compute

Idle resources / Unmanaged

VIDAware Compute Containerization System Architecture

Elastic Container × GPU × AI Pod Architecture

VIDAWARE × AI Pod Orchestration

Multi-Source Streams → AI Pod → Dynamic GPU Resource Scheduling

Input Streams
PRIMARY POD
STANDBY POD
Sources auto-dispatch → Pod scheduling → Lowest GPU load first
GPU SERVER1
CUDA
DEEP_LEARNING
18%
GPU SERVER2
CUDA
GENERAL_COMPUTE
29%
GPU SERVER3
CUDA
EDGE_INFERENCE
44%
GPU SERVER4
CUDA
VIDEO_TRANSCODE
57%
GPU SERVER5
CUDA
MODEL_SERVING
68%
GPU SERVER6
CUDA
BATCH_INFERENCE
83%

Management & Operations Layer: Commercialization and Security

Ensures data security between tenants and supports compute-token-based business models.

Multi-Tenant Compute Token Billing

Measures resource usage across projects and converts it into token deductions. The chart shows token consumption by major tenants across different services.

Face Recog License Plate Event Detect
Identity Authentication & Security

SSO / OIDC, API key management, and end-to-end TLS encryption.

Multi-Tenant Isolation

Namespace + RBAC ensures complete resource isolation between tenants.

Real-Time Alert System

Automatic alerts via Email / LINE / SMS.