> 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/reference/cli/runai/inference/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

## Docs

- [runai inference](https://docs.nvidia.com/run-ai/self-hosted/v3.0/reference/cli/runai/inference/runai-inference.md)
- [runai inference bash](https://docs.nvidia.com/run-ai/self-hosted/v3.0/reference/cli/runai/inference/runai-inference-bash.md)
- [runai inference delete](https://docs.nvidia.com/run-ai/self-hosted/v3.0/reference/cli/runai/inference/runai-inference-delete.md)
- [runai inference describe](https://docs.nvidia.com/run-ai/self-hosted/v3.0/reference/cli/runai/inference/runai-inference-describe.md)
- [runai inference distributed](https://docs.nvidia.com/run-ai/self-hosted/v3.0/reference/cli/runai/inference/runai-inference-distributed.md)
- [runai inference distributed bash](https://docs.nvidia.com/run-ai/self-hosted/v3.0/reference/cli/runai/inference/runai-inference-distributed-bash.md)
- [runai inference distributed delete](https://docs.nvidia.com/run-ai/self-hosted/v3.0/reference/cli/runai/inference/runai-inference-distributed-delete.md)
- [runai inference distributed describe](https://docs.nvidia.com/run-ai/self-hosted/v3.0/reference/cli/runai/inference/runai-inference-distributed-describe.md)
- [runai inference distributed exec](https://docs.nvidia.com/run-ai/self-hosted/v3.0/reference/cli/runai/inference/runai-inference-distributed-exec.md)
- [runai inference distributed list](https://docs.nvidia.com/run-ai/self-hosted/v3.0/reference/cli/runai/inference/runai-inference-distributed-list.md)
- [runai inference distributed logs](https://docs.nvidia.com/run-ai/self-hosted/v3.0/reference/cli/runai/inference/runai-inference-distributed-logs.md)
- [runai inference distributed port-forward](https://docs.nvidia.com/run-ai/self-hosted/v3.0/reference/cli/runai/inference/runai-inference-distributed-port-forward.md)
- [runai inference distributed scale](https://docs.nvidia.com/run-ai/self-hosted/v3.0/reference/cli/runai/inference/runai-inference-distributed-scale.md)
- [runai inference distributed submit](https://docs.nvidia.com/run-ai/self-hosted/v3.0/reference/cli/runai/inference/runai-inference-distributed-submit.md)
- [runai inference exec](https://docs.nvidia.com/run-ai/self-hosted/v3.0/reference/cli/runai/inference/runai-inference-exec.md)
- [runai inference list](https://docs.nvidia.com/run-ai/self-hosted/v3.0/reference/cli/runai/inference/runai-inference-list.md)
- [runai inference logs](https://docs.nvidia.com/run-ai/self-hosted/v3.0/reference/cli/runai/inference/runai-inference-logs.md)
- [runai inference nim](https://docs.nvidia.com/run-ai/self-hosted/v3.0/reference/cli/runai/inference/runai-inference-nim.md)
- [runai inference nim bash](https://docs.nvidia.com/run-ai/self-hosted/v3.0/reference/cli/runai/inference/runai-inference-nim-bash.md)
- [runai inference nim delete](https://docs.nvidia.com/run-ai/self-hosted/v3.0/reference/cli/runai/inference/runai-inference-nim-delete.md)
- [runai inference nim describe](https://docs.nvidia.com/run-ai/self-hosted/v3.0/reference/cli/runai/inference/runai-inference-nim-describe.md)
- [runai inference nim exec](https://docs.nvidia.com/run-ai/self-hosted/v3.0/reference/cli/runai/inference/runai-inference-nim-exec.md)
- [runai inference nim list](https://docs.nvidia.com/run-ai/self-hosted/v3.0/reference/cli/runai/inference/runai-inference-nim-list.md)
- [runai inference nim logs](https://docs.nvidia.com/run-ai/self-hosted/v3.0/reference/cli/runai/inference/runai-inference-nim-logs.md)
- [runai inference nim port-forward](https://docs.nvidia.com/run-ai/self-hosted/v3.0/reference/cli/runai/inference/runai-inference-nim-port-forward.md)
- [runai inference nim scale](https://docs.nvidia.com/run-ai/self-hosted/v3.0/reference/cli/runai/inference/runai-inference-nim-scale.md)
- [runai inference nim submit](https://docs.nvidia.com/run-ai/self-hosted/v3.0/reference/cli/runai/inference/runai-inference-nim-submit.md)
- [runai inference nim update](https://docs.nvidia.com/run-ai/self-hosted/v3.0/reference/cli/runai/inference/runai-inference-nim-update.md)
- [runai inference port-forward](https://docs.nvidia.com/run-ai/self-hosted/v3.0/reference/cli/runai/inference/runai-inference-port-forward.md)
- [runai inference standard](https://docs.nvidia.com/run-ai/self-hosted/v3.0/reference/cli/runai/inference/runai-inference-standard.md)
- [runai inference standard bash](https://docs.nvidia.com/run-ai/self-hosted/v3.0/reference/cli/runai/inference/runai-inference-standard-bash.md)
- [runai inference standard delete](https://docs.nvidia.com/run-ai/self-hosted/v3.0/reference/cli/runai/inference/runai-inference-standard-delete.md)
- [runai inference standard describe](https://docs.nvidia.com/run-ai/self-hosted/v3.0/reference/cli/runai/inference/runai-inference-standard-describe.md)
- [runai inference standard exec](https://docs.nvidia.com/run-ai/self-hosted/v3.0/reference/cli/runai/inference/runai-inference-standard-exec.md)
- [runai inference standard list](https://docs.nvidia.com/run-ai/self-hosted/v3.0/reference/cli/runai/inference/runai-inference-standard-list.md)
- [runai inference standard logs](https://docs.nvidia.com/run-ai/self-hosted/v3.0/reference/cli/runai/inference/runai-inference-standard-logs.md)
- [runai inference standard port-forward](https://docs.nvidia.com/run-ai/self-hosted/v3.0/reference/cli/runai/inference/runai-inference-standard-port-forward.md)
- [runai inference standard submit](https://docs.nvidia.com/run-ai/self-hosted/v3.0/reference/cli/runai/inference/runai-inference-standard-submit.md)
- [runai inference standard update](https://docs.nvidia.com/run-ai/self-hosted/v3.0/reference/cli/runai/inference/runai-inference-standard-update.md)
- [runai inference submit](https://docs.nvidia.com/run-ai/self-hosted/v3.0/reference/cli/runai/inference/runai-inference-submit.md)
- [runai inference update](https://docs.nvidia.com/run-ai/self-hosted/v3.0/reference/cli/runai/inference/runai-inference-update.md)