LLMOps
Learn what LLMOps manages when prompts, retrieval, model services, and tools change an LLM application.
-
-
MLOps
Understand how MLOps connects model development, evaluation, deployment, monitoring, and recovery.
-
Latency Guardrails
Define latency guardrails with measurement boundaries, percentiles, realistic load, and a clear response when a limit is exceeded.
-
Cloud Inference
Distinguish cloud inference from training and deployment, and compare online, asynchronous, batch, and on-device execution.
-
Caching in Machine Learning
Learn when ML caches can safely reuse results, with model versions, data freshness, permissions, expiry, and cache failures in view.
-
Model Registry
Learn how a model registry tracks versions and metadata without replacing evaluation, deployment, or inference.
-
Model Artifact
Understand the saved model representation and the dependencies needed to load and use it correctly.
-
Serving
Understand serving as providing usable results, and distinguish it from storage, inference, and deployment.