← 🧠 Machine Learning

🚦 Serving Cluster

Active replicas:
P95 latency:
Throughput:
Queue depth:
Dropped (overload): 0
FPS:
Drag — rotate · Scroll — zoom

🚦 Deployment Hyperparameters

A live 3D model-serving cluster where a load balancer routes request traffic to a ring of replica pods — batching, autoscaling and canary traffic split all reshape latency, throughput and queue depth in real time.

🔬 What It Demonstrates

Batch size trades per-request latency for per-replica throughput; too few replicas under heavy traffic builds a queue and starts dropping requests; autoscaling reacts to that queue depth the way a production orchestrator would.

🎮 How to Use

Raise traffic and watch latency and queue depth respond. Adjust batch size and replica count to find the trade-off, or flip on autoscaling and let the cluster size itself. Route a slice of traffic to the teal canary pods to see a rollout in isolation.

💡 Did You Know?

Canary deployments get their name from "canary in a coal mine" — routing a small, monitored slice of live traffic to a new model version lets teams catch regressions before they reach every user.