AI in Malta
- AI in Malta: Server Configuration & Infrastructure
This article details the server configuration powering the "AI in Malta" project, a research initiative focused on applying artificial intelligence to local challenges. It's designed as a technical overview for newcomers to our MediaWiki infrastructure and will cover hardware, software, networking, and security aspects.
Project Overview
The "AI in Malta" project requires significant computational resources for training and deploying machine learning models. These models range from image recognition for archaeological site analysis (Archaeological_Data_Processing) to natural language processing for Maltese language support (Maltese_NLP). The server infrastructure has been designed for scalability, reliability, and security. This infrastructure is constantly monitored by the Server_Monitoring_Team.
Hardware Specifications
Our primary compute cluster consists of high-performance servers, storage arrays, and networking equipment.
| Component | Specification | Quantity |
|---|---|---|
| CPU | AMD EPYC 7763 (64-core) | 8 |
| RAM | 256 GB DDR4 ECC Registered | 8 |
| GPU | NVIDIA A100 (80GB) | 4 |
| Storage (OS) | 1 TB NVMe SSD | 8 |
| Storage (Data) | 4 x 16 TB SAS HDD (RAID 10) | 2 Arrays |
| Network Interface | 100 Gbps Mellanox ConnectX-6 | 8 |
We also maintain a secondary backup cluster for disaster recovery and model versioning (Data_Backup_Procedures). The backup cluster has slightly lower specifications, but provides sufficient redundancy.
Software Stack
The software stack is built around a Linux distribution, optimized for machine learning workloads.
| Layer | Software | Version |
|---|---|---|
| Operating System | Ubuntu Server 22.04 LTS | 22.04 |
| Containerization | Docker | 20.10 |
| Orchestration | Kubernetes | 1.24 |
| Machine Learning Frameworks | TensorFlow, PyTorch, scikit-learn | 2.9, 1.13, 1.2 |
| Database | PostgreSQL | 14 |
| Version Control | Git | 2.34 |
All code is managed using Git_Repository_Access and deployed via automated CI/CD pipelines managed by Jenkins_Configuration. We utilize a microservices architecture, with each AI model deployed as a separate containerized service. Access to the Kubernetes cluster is controlled via RBAC_Configuration.
Networking & Security
The server infrastructure is hosted in a secure data center in Malta. Network access is restricted to authorized personnel and services.
| Aspect | Configuration |
|---|---|
| Network Topology | Virtual Private Cloud (VPC) |
| Firewall | iptables, UFW |
| Intrusion Detection System | Suricata |
| VPN Access | OpenVPN |
| Authentication | Multi-Factor Authentication (MFA) using Authentication_Methods |
| Monitoring | Prometheus, Grafana (see Server_Monitoring_Dashboard) |
All data is encrypted at rest and in transit. Regular security audits are conducted by the Security_Audit_Team and vulnerability scans are performed weekly. We adhere to the Data_Privacy_Policy to protect sensitive information. Network segmentation is employed to isolate different environments (development, staging, production). The system is regularly patched using Automated_Patching_System.
Data Storage & Management
Data is stored on a high-performance storage array configured in RAID 10 for redundancy and performance. We utilize a combination of object storage (for large datasets) and block storage (for databases and virtual machines). Data is backed up daily to an offsite location. Data lifecycle management is handled by Data_Lifecycle_Management_Procedure.
Future Scalability
The current infrastructure is designed to be scalable. We plan to add additional GPU servers in the future to support growing computational demands. We are also evaluating the use of cloud-based services for burst capacity (Cloud_Integration_Plan). The system architecture allows for horizontal scaling of both compute and storage resources.
Main Page Server_Documentation Networking_Guidelines Security_Policies Data_Management Troubleshooting_Guide Contact_Support Server_Monitoring_Dashboard Jenkins_Configuration RBAC_Configuration Authentication_Methods Data_Backup_Procedures Data_Privacy_Policy Automated_Patching_System Archaeological_Data_Processing Maltese_NLP Cloud_Integration_Plan Git_Repository_Access Data_Lifecycle_Management_Procedure Server_Monitoring_Team Security_Audit_Team
Intel-Based Server Configurations
| Configuration | Specifications | Benchmark |
|---|---|---|
| Core i7-6700K/7700 Server | 64 GB DDR4, NVMe SSD 2 x 512 GB | CPU Benchmark: 8046 |
| Core i7-8700 Server | 64 GB DDR4, NVMe SSD 2x1 TB | CPU Benchmark: 13124 |
| Core i9-9900K Server | 128 GB DDR4, NVMe SSD 2 x 1 TB | CPU Benchmark: 49969 |
| Core i9-13900 Server (64GB) | 64 GB RAM, 2x2 TB NVMe SSD | |
| Core i9-13900 Server (128GB) | 128 GB RAM, 2x2 TB NVMe SSD | |
| Core i5-13500 Server (64GB) | 64 GB RAM, 2x500 GB NVMe SSD | |
| Core i5-13500 Server (128GB) | 128 GB RAM, 2x500 GB NVMe SSD | |
| Core i5-13500 Workstation | 64 GB DDR5 RAM, 2 NVMe SSD, NVIDIA RTX 4000 |
AMD-Based Server Configurations
| Configuration | Specifications | Benchmark |
|---|---|---|
| Ryzen 5 3600 Server | 64 GB RAM, 2x480 GB NVMe | CPU Benchmark: 17849 |
| Ryzen 7 7700 Server | 64 GB DDR5 RAM, 2x1 TB NVMe | CPU Benchmark: 35224 |
| Ryzen 9 5950X Server | 128 GB RAM, 2x4 TB NVMe | CPU Benchmark: 46045 |
| Ryzen 9 7950X Server | 128 GB DDR5 ECC, 2x2 TB NVMe | CPU Benchmark: 63561 |
| EPYC 7502P Server (128GB/1TB) | 128 GB RAM, 1 TB NVMe | CPU Benchmark: 48021 |
| EPYC 7502P Server (128GB/2TB) | 128 GB RAM, 2 TB NVMe | CPU Benchmark: 48021 |
| EPYC 7502P Server (128GB/4TB) | 128 GB RAM, 2x2 TB NVMe | CPU Benchmark: 48021 |
| EPYC 7502P Server (256GB/1TB) | 256 GB RAM, 1 TB NVMe | CPU Benchmark: 48021 |
| EPYC 7502P Server (256GB/4TB) | 256 GB RAM, 2x2 TB NVMe | CPU Benchmark: 48021 |
| EPYC 9454P Server | 256 GB RAM, 2x2 TB NVMe |
Order Your Dedicated Server
Configure and order your ideal server configuration
Need Assistance?
- Telegram: @powervps Servers at a discounted price
⚠️ *Note: All benchmark scores are approximate and may vary based on configuration. Server availability subject to stock.* ⚠️