# `HfHub.InferenceEndpoints.ScalingConfig`
[🔗](https://github.com/North-Shore-AI/hf_hub_ex/blob/v0.3.1/lib/hf_hub/inference_endpoints/scaling_config.ex#L1)

Scaling configuration for an inference endpoint.

# `t`

```elixir
@type t() :: %HfHub.InferenceEndpoints.ScalingConfig{
  max_replica: pos_integer() | nil,
  min_replica: non_neg_integer() | nil,
  scale_to_zero_timeout: non_neg_integer() | nil
}
```

# `from_response`

```elixir
@spec from_response(map()) :: t()
```

Creates a ScalingConfig struct from an API response.

---

*Consult [api-reference.md](api-reference.md) for complete listing*