> ## Documentation Index
> Fetch the complete documentation index at: https://vastai-80aa3a82-auto-cli-sdk-preview-pr-398.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# VastAI.update_workergroup

Update an existing autoscale worker group.

## Signature

```python theme={null}
VastAI.update_workergroup(
    id: int,
    min_load: Optional[float] = None,
    target_util: Optional[float] = None,
    cold_mult: Optional[float] = None,
    cold_workers: Optional[int] = None,
    test_workers: Optional[int] = None,
    gpu_ram: Optional[float] = None,
    template_hash: Optional[str] = None,
    template_id: Optional[int] = None,
    search_params: Optional[str] = None,
    no_default: bool = False,
    launch_args: Optional[str] = None,
    endpoint_name: Optional[str] = None,
    endpoint_id: Optional[int] = None
) -> dict
```

## Parameters

<ParamField path="id" type="int" required>
  id of autoscale group to update
</ParamField>

<ParamField path="min_load" type="Optional[float]">
  minimum floor load in perf units/s  (token/s for LLms)
</ParamField>

<ParamField path="target_util" type="Optional[float]">
  target capacity utilization (fraction, max 1.0, default 0.9)
</ParamField>

<ParamField path="cold_mult" type="Optional[float]">
  cold/stopped instance capacity target as multiple of hot capacity target (default 2.5)
</ParamField>

<ParamField path="cold_workers" type="Optional[int]">
  min number of workers to keep 'cold' for this workergroup
</ParamField>

<ParamField path="test_workers" type="Optional[int]">
  number of workers to create to get an performance estimate for while initializing workergroup (default 3)
</ParamField>

<ParamField path="gpu_ram" type="Optional[float]">
  estimated GPU RAM req  (independent of search string)
</ParamField>

<ParamField path="template_hash" type="Optional[str]">
  template hash (**Note**: if you use this field, you can skip search\_params, as they are automatically inferred from the template)
</ParamField>

<ParamField path="template_id" type="Optional[int]">
  template id
</ParamField>

<ParamField path="search_params" type="Optional[str]">
  search param string for search offers    ex: "gpu\_ram>=23 num\_gpus=2 gpu\_name=RTX\_4090 inet\_down>200 direct\_port\_count>2 disk\_space>=64"
</ParamField>

<ParamField path="no_default" type="bool">
  Disable default search param query args
</ParamField>

<ParamField path="launch_args" type="Optional[str]">
  launch args  string for create instance  ex: "--onstart onstart\_wget.sh  --env '-e ONSTART\_PATH=[https://s3.amazonaws.com/public.vast.ai/onstart\_OOBA.sh](https://s3.amazonaws.com/public.vast.ai/onstart_OOBA.sh)' --image atinoda/text-generation-webui:default-nightly --disk 64"
</ParamField>

<ParamField path="endpoint_name" type="Optional[str]">
  deployment endpoint name (allows multiple workergroups to share same deployment endpoint)
</ParamField>

<ParamField path="endpoint_id" type="Optional[int]">
  deployment endpoint id (allows multiple workergroups to share same deployment endpoint)
</ParamField>

## Returns

`dict`

## Example

```python theme={null}
from vastai import VastAI

client = VastAI(api_key="YOUR_API_KEY")
result = client.update_workergroup(id=12345)
print(result)
```