> For clean Markdown content of this page, append .md to this URL. For the complete documentation index, see https://docs.nvidia.com/dynamo/llms.txt. For full content including API reference and SDK examples, see https://docs.nvidia.com/dynamo/llms-full.txt.

# User Guides

## Docs

- [KV Cache Aware Routing](https://docs.nvidia.com/dynamo/v-0-9-1/user-guides/kv-cache-aware-routing.md): Enable KV-aware routing using Router for Dynamo deployments
- [Disaggregated Serving](https://docs.nvidia.com/dynamo/v-0-9-1/user-guides/disaggregated-serving.md): Find optimal prefill/decode configuration for disaggregated serving deployments
- [KV Cache Offloading](https://docs.nvidia.com/dynamo/v-0-9-1/user-guides/kv-cache-offloading.md): Enable KV offloading using KV Block Manager (KVBM) for Dynamo deployments
- [Dynamo Benchmarking Guide](https://docs.nvidia.com/dynamo/v-0-9-1/user-guides/dynamo-benchmarking.md)
- [Multimodality Support](https://docs.nvidia.com/dynamo/v-0-9-1/user-guides/multimodality-support.md): Deploy multimodal models with image, video, and audio support in Dynamo
- [SGLang Multimodal](https://docs.nvidia.com/dynamo/v-0-9-1/user-guides/multimodality-support/sg-lang-multimodal.md)
- [TensorRT-LLM Multimodal](https://docs.nvidia.com/dynamo/v-0-9-1/user-guides/multimodality-support/tensor-rt-llm-multimodal.md)
- [vLLM Multimodal](https://docs.nvidia.com/dynamo/v-0-9-1/user-guides/multimodality-support/v-llm-multimodal.md)
- [Tool Calling](https://docs.nvidia.com/dynamo/v-0-9-1/user-guides/tool-calling.md): Connect Dynamo to external tools and services using function calling
- [LoRA Adapters](https://docs.nvidia.com/dynamo/v-0-9-1/user-guides/lo-ra-adapters.md): Serve fine-tuned LoRA adapters with dynamic loading and routing in Dynamo
- [Observability (Local)](https://docs.nvidia.com/dynamo/v-0-9-1/user-guides/observability-local.md): Monitor Dynamo deployments with metrics, logging, and tracing
- [Prometheus + Grafana Setup](https://docs.nvidia.com/dynamo/v-0-9-1/user-guides/observability-local/prometheus-grafana-setup.md)
- [Metrics](https://docs.nvidia.com/dynamo/v-0-9-1/user-guides/observability-local/metrics.md)
- [Metrics Developer Guide](https://docs.nvidia.com/dynamo/v-0-9-1/user-guides/observability-local/metrics-developer-guide.md)
- [Health Checks](https://docs.nvidia.com/dynamo/v-0-9-1/user-guides/observability-local/health-checks.md)
- [Tracing](https://docs.nvidia.com/dynamo/v-0-9-1/user-guides/observability-local/tracing.md)
- [Logging](https://docs.nvidia.com/dynamo/v-0-9-1/user-guides/observability-local/logging.md)
- [Fault Tolerance](https://docs.nvidia.com/dynamo/v-0-9-1/user-guides/fault-tolerance.md): Handle failures gracefully with request migration, cancellation, and graceful shutdown
- [Request Migration](https://docs.nvidia.com/dynamo/v-0-9-1/user-guides/fault-tolerance/request-migration.md)
- [Request Cancellation](https://docs.nvidia.com/dynamo/v-0-9-1/user-guides/fault-tolerance/request-cancellation.md)
- [Graceful Shutdown](https://docs.nvidia.com/dynamo/v-0-9-1/user-guides/fault-tolerance/graceful-shutdown.md)
- [Request Rejection](https://docs.nvidia.com/dynamo/v-0-9-1/user-guides/fault-tolerance/request-rejection.md)
- [Testing](https://docs.nvidia.com/dynamo/v-0-9-1/user-guides/fault-tolerance/testing.md)
- [Writing Python Workers in Dynamo](https://docs.nvidia.com/dynamo/v-0-9-1/user-guides/writing-python-workers-in-dynamo.md): Create custom Python workers and engines for Dynamo