Hey guys, I've added standard health check endpoints to ClearML Serving!

🔍 Issue: # 94 (Add Standard Health Check Endpoints)
🔗 PR: # 95

The PR introduces:

• GET /health - Basic service status
• GET /readiness - Service readiness with model/GPU checks
• GET /liveness - Lightweight liveness check
• GET /metrics - Service metrics (uptime, request counts, etc.)

These will make it easier to monitor and orchestrate ClearML Serving in production. Would love your feedback!