---
# Code generated by go run ./scripts/gendocs. DO NOT EDIT.
title: "llm-helper up"
description: "Start serving a profile alongside anything already running"
---

<!-- DO NOT EDIT | GENERATED CONTENT -->

## Usage

```console
llm-helper up <profile> [flags]
```

## Options

### --kv-cache

|      |          |
| ---- | -------- |
| Type | `string` |

fixed KV cache size in bytes, e.g. 20G

### --mem-util

|      |          |
| ---- | -------- |
| Type | `string` |

fraction of GPU memory this model may use, e.g. 0.4

### --no-follow

|      |        |
| ---- | ------ |
| Type | `bool` |

return as soon as the server is started instead of watching the boot

### --port

|      |          |
| ---- | -------- |
| Type | `string` |

port to serve on (default: the next free one from PORT)

### --timeout

|      |            |
| ---- | ---------- |
| Type | `duration` |

give up waiting after this long (default: wait forever)

### --wait

|      |        |
| ---- | ------ |
| Type | `bool` |

block until the endpoint is healthy, without streaming logs