ALL SYSTEMS OPERATIONAL
UPTIME 99.5%
Distributed REST API · Production

Fault-Tolerant ML Model
Deployment Platform

Serving ML predictions at <150ms latency. Containerised with Docker, orchestrated via Kubernetes across distributed cloud infrastructure.

Flask Docker Kubernetes AWS GitHub Actions REST API CI/CD
Avg Latency
—
target <150ms
Uptime
99.5%
last 30 days
Active Pods
3
k8s replicas
Requests/min
—
live traffic
CI/CD Pipeline — GitHub Actions
✓ Last deploy: 2m ago
📦
Build
✓ passed
──▶
🧪
Test
✓ passed
──▶
🐳
Docker
✓ pushed
──▶
☸️
K8s Deploy
✓ live
──▶
📊
Monitor
✓ healthy
Live Latency (ms)
last 20 requests
Live API Inference
POST /predict
POST api.mldeploy.prod/v1/predict
Request Payload (JSON)
response — flask api server
$ Waiting for inference request...
Kubernetes Pods
3/3 RUNNING
ml-deploy-7d4f9-xk2p1
us-east-1a · docker:v2.1.0 · 14d
12%
ml-deploy-7d4f9-mn8r3
us-west-2b · docker:v2.1.0 · 14d
9%
ml-deploy-7d4f9-qs5t7
ap-south-1 · docker:v2.1.0 · 14d
17%
System Health
CPU Usage 13%
Memory 2.1 / 4 GB
Network I/O 48 MB/s