> This page is for Self-Hosted, version v3.0 (default).
> For other versions, use one of these documentation indexes:
> - v3.0 (default): https://docs.nvidia.com/run-ai/self-hosted/v3.0/llms.txt
> - v2.26: https://docs.nvidia.com/run-ai/self-hosted/v2.26/llms.txt
> - v2.25: https://docs.nvidia.com/run-ai/self-hosted/v2.25/llms.txt
> - v2.24: https://docs.nvidia.com/run-ai/self-hosted/v2.24/llms.txt

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

# runai inference distributed describe

describe a distributed inference workload

```
runai inference distributed describe [WORKLOAD_NAME] [flags]
```

### Examples

```
# Describe a workload with a default project
runai inference distributed describe <workload-name>

# Describe a workload in a specific project
runai inference distributed describe <workload-name> -p <project-name>

# Describe a workload by UUID
runai inference distributed describe --uuid=<workload-id>

# Describe a workload with specific output format
runai inference distributed describe <workload-name> -o json

# Describe a workload with specific sections
runai inference distributed describe <workload-name> --general --compute --pods --events --networks

# Describe a workload with container details and custom limits
runai inference distributed describe <workload-name> --containers --pod-limit 20 --event-limit 100
```

### Options

```
      --compute             Show compute resources information (CPU, GPU, memory, etc.). (default true)
      --containers          Include container-level details in pod information.
      --event-limit int32   Limit the number of events displayed. Use -1 for no limit. (default 50)
      --events              Show recent events for the resource. (default true)
      --general             Show general resource information. (default true)
  -h, --help                help for describe
      --networks            Show network-related information. (default true)
  -o, --output string       Output format: table, json, or yaml. Default is table. (default "table")
      --pod-limit int32     Limit the number of pods displayed. Use -1 for no limit. (default 10)
      --pods                Show information about pods associated with the resource. (default true)
  -p, --project string      Specify the project for the command to use. Defaults to the project set in the context, if any. Use 'runai project set <project>' to set the default.
      --sortEvents string   Sort events in ascending or descending order. Valid values: asc, desc. (default "asc")
      --storage             Show storage information (PVCs, ConfigMaps, Secrets, etc.). (default true)
```

### Options inherited from parent commands

```
      --config-file string   config file name; can be set by environment variable RUNAI_CLI_CONFIG_FILE (default "config.json")
      --config-path string   config path; can be set by environment variable RUNAI_CLI_CONFIG_PATH
  -d, --debug                enable debug mode
  -q, --quiet                enable quiet mode, suppress all output except error messages
      --verbose              enable verbose mode
```

### SEE ALSO

* [runai inference distributed](/run-ai/self-hosted/reference/cli/runai/inference/runai-inference-distributed)	 - Runs multiple coordinated inference processes across multiple nodes. Required for models too large to run on a single node.