Tag: MLOps
-
Model Drift Detection Failed Silently: Evidently AI Fix
Fix Evidently AI's silent drift detection failures with schema validation. Real production errors, Wasserstein metrics, and monitoring setup.
-
Triton vs TorchServe: How I Cut $800/Month in GPU Costs
Triton cut my inference costs 52% vs TorchServe. GPU utilization jumped from 23% to 81%. Here's what profiling actually revealed.
-
MLflow + FastAPI: $2K/Month Model Serving Side Project
MLflow tracking + FastAPI serving generates $2K/month from gradient boosting churn models. Real architecture, deployment costs included.
-
Smart Factory AI Pipeline: End-to-End Case Study
Smart factory AI that survives edge throttling and RL constraints: 3 deployment fixes from thermal crashes to scheduler violations.