> 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.

# Model Loading

## Docs

- [Fast Model Weight Loading](https://docs.nvidia.com/dynamo/dev/kubernetes/model-deployment/model-loading/fast-model-loading.md): Cut cold-start weight-load time on shared PVC storage with a concurrent loader and correct filesystem layout
- [Restore Workers with Dynamo Snapshot](https://docs.nvidia.com/dynamo/dev/kubernetes/model-deployment/model-loading/dynamo-snapshot-experimental.md): Capture an initialized TensorRT-LLM worker and verify that a restored worker serves requests
- [Load Models from MatrixHub](https://docs.nvidia.com/dynamo/dev/kubernetes/model-deployment/model-loading/matrix-hub.md): Configure Dynamo on Kubernetes to retrieve model weights from an in-cluster MatrixHub registry.