| # Tutorials | |
| Step-by-step tutorials to guide you through complete workflows, from data preparation to serving trained models in production. | |
| ## [Train a Speculator](train.md) | |
| The main end-to-end walkthrough: prepare data, generate hidden states, train, and serve. Covers Eagle-3, P-EAGLE, DFlash, DSpark, and MTP, in online, offline, or hybrid mode -- pick your algorithm and mode at the top of the page. | |
| ## [Multi-Node Training](multi_node_training.md) | |
| Stream hidden states between separate extraction and training nodes with the Mooncake backend when the target model does not fit on one node or shared storage is unavailable. | |
| ## [Response Regeneration](response_regeneration.md) | |
| Regenerate dataset responses using your target model for improved drafter alignment. Recommended before training. | |
| ## [Evaluating Model Performance](evaluating_performance.md) | |
| Benchmark and evaluate your trained speculator models. | |
| ## [Serve in vLLM](serve_vllm.md) | |
| Deploy your trained speculator models in vLLM for production inference. | |