| title | Feature Guides |
|---|---|
| subtitle | Start with Dynamo's core serving optimizations, then branch into operations and model capabilities. |
Use these guides after you have Dynamo running and want to improve serving behavior, operate a deployment, or adapt Dynamo to a new workload.
Most deployments start with the core performance loop:
| Step | Guide | Use when |
|---|---|---|
| 1 | KV Cache Aware Routing | Route requests to workers that already hold useful KV cache. |
| 2 | Disaggregated Serving | Scale prefill and decode workers independently. |
| 3 | KV Cache Offloading | Extend usable cache capacity beyond GPU memory. |
| 4 | Benchmarking | Compare configurations before you move to production. |
| Goal | Start with |
|---|---|
| Make serving more resilient | Fault Tolerance |
| Monitor local deployments | Observability (Local) |
| Reproduce traffic without a full engine | Mocker Engine Simulation |
| Add structured model outputs | Tool Calling and Reasoning |
| Build agent workloads | Agents |
| Serve specialized workloads | LoRA Adapters, Multimodal, and Diffusion |
For cluster deployments, pair these guides with the Kubernetes Deployment docs. The same features can be explored locally, then expressed through Dynamo's Kubernetes-native CRDs and operator when you move to a shared GPU cluster.