A production-intelligence node for machine vision, telemetry, predictive maintenance and low-latency factory AI.
This brief explains where the baseline fits, the software and operating model it supports, and the evidence Axiotech should use to validate a final configuration. Indicative specifications remain subject to component availability, export compliance and formal quotation.
Baseline architecture
One 4U node; 96 AMD EPYC cores; 768GB ECC DDR5; two NVIDIA RTX PRO 5000 48GB GPUs; protected local/NAS data services.
The current compute node is based on the Supermicro AS-4125GS-TNRT / CSE-418G2TS 4U rack platform, integrated with matched rails, power, management, networking and rack infrastructure as required.
Best-fit workloads
Multi-camera inspection, predictive maintenance, production telemetry, quality analytics, robot perception and low-latency factory AI with a second GPU available for isolation or retraining.
Two 48GB GPUs allow live inference to remain isolated from retraining, validation or a second production line.
Recommended software stack
CUDA, DeepStream, TensorRT/Triton, OpenCV, Kafka or MQTT, OPC UA/ADS connectors, time-series databases, Prometheus/Grafana and MLflow.
Pin host drivers and infrastructure separately from versioned application containers. Record source, image, dataset/model and hardware allocation with each benchmark or production release.
Deployment pattern
Connect through controlled industrial gateways, buffer inputs, run containerised inference and retain governed evidence on protected storage. Keep actuation and certified safety outside the AI service.
Define monitoring, identity, backup, change control and workload ownership at the same time as compute. Multi-user platforms require resource allocation and quotas; production services require health, overload and rollback behaviour.
Sizing boundary
Production availability requires explicit camera/network failure modes, retention policies and change control. GPU capacity alone does not create a validated production system.
Final sizing should use representative code, data, concurrency and service objectives. Aggregate core, RAM or VRAM figures do not by themselves predict application performance.
Commissioning and acceptance
Load-test all production streams, measure sensor-to-decision p99 latency, inject camera/network loss, validate recovery and compare alerts/decisions against supervised production evidence.
Axiotech should retain the resulting configuration, firmware/driver baseline, environment manifest, benchmark data and recovery procedure as the system acceptance pack.
Primary technical references
References are provided for software architecture and implementation planning. Validate the versions, licences, support matrix and regulated-use requirements applicable to the final deployment.