#model-serving

A guide to the GPU infrastructure, inference framework, and inference optimization layers, with a single map of the end-to-end LLM inference request path and per-layer tuning levers — inference gateway, prefill/decode disaggregation, KV cache-aware routing, LMCache, and cache-hit strategy.

Comparing SageMaker HyperPod Inference Operator's managed KV cache, intelligent routing, and DPD with a Tiered Gateway, and clarifying its role and limitations as an L2 inference routing layer.

Architecture concepts, distributed deployment strategies, and performance optimization principles for Mixture of Experts models

Custom model deployment, fine-tuning pipelines, MLOps orchestration, continuous training pipelines