Prerequisites
Before installing EVA, please review the system requirements and environment configuration. EVA operates on a Kubernetes-based architecture and leverages various AI models, including Vision Models, LLMs, and VLMs. Therefore, GPU resources are required.
Server Requirements
EVA operates reliably on environments that meet or exceed the minimum specifications. In production environments, server specifications can be flexibly adjusted based on detection frequency, criticality, and concurrency.
Recommended Server Specification
EVA can be operated as a single integrated server deployment that combines App, Vision, and Agent. This unified server handles camera connection management, video analysis, contextual decision-making, and alert generation. The table below describes the minimum recommended specification for a 100-camera deployment.
| Item | Minimum Specification |
|---|---|
| CPU | 32 Cores or higher |
| RAM | 96 GB or higher |
| GPU | RTX PRO 6000 Blackwell |
| Storage | SSD 2 TB |
| OS | Ubuntu 24.04 |
💡 A unified deployment simplifies initial setup and operations, making it practical for PoC and small-to-medium environments.
⚠️ Actual hardware requirements may vary depending on camera resolution, number of cameras, and detection intervals.
For large-scale environments, scaling up integrated server resources is recommended.
Kubernetes Environment
EVA operates within a Kubernetes environment and requires the following configuration in either cloud or on-premise deployments:
- Kubernetes cluster
- GPU access configuration (e.g.,
nvidia-device-plugin) - Ubuntu 24.04–based nodes
- CUDA 12 or higher
- Helm CLI (v3.0 or higher)
💡 In cloud environments, EVA App, Vision, and Agent can also be deployed together in a unified structure for simpler operations.
🧩 In on-premise environments, a unified configuration with shared GPU resources can be used to build a cost-efficient infrastructure.