> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.nvidia.com/run-ai/self-hosted/v3.0/documentation/workloads-in-nvidia-run-ai/workload-templates/inference-templates/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.nvidia.com/run-ai/_mcp/server.

# Inference Templates

## Docs

- [NVIDIA NIM Inference Templates](https://docs.nvidia.com/run-ai/self-hosted/v3.0/documentation/workloads-in-nvidia-run-ai/workload-templates/inference-templates/nvidia-nim-inference-templates.md)
- [vLLM Inference Templates](https://docs.nvidia.com/run-ai/self-hosted/v3.0/documentation/workloads-in-nvidia-run-ai/workload-templates/inference-templates/v-llm-inference-templates.md)
- [Custom Inference Templates](https://docs.nvidia.com/run-ai/self-hosted/v3.0/documentation/workloads-in-nvidia-run-ai/workload-templates/inference-templates/custom-inference-templates.md)