> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.nvidia.com/nemo/curator/llms.txt.
> For full documentation content, see https://docs.nvidia.com/nemo/curator/llms-full.txt.
# nemo_curator.core.serve.base
## Module Contents
### Classes
| Name | Description |
| -------------------------------------------------------------------- | ---------------------------------------------------------------------------------- |
| [`BaseModelConfig`](#nemo_curator-core-serve-base-BaseModelConfig) | Base public model config shared by inference backends. |
| [`BaseServerConfig`](#nemo_curator-core-serve-base-BaseServerConfig) | Base server-level config; subclasses declare which model config types they accept. |
| [`InferenceBackend`](#nemo_curator-core-serve-base-InferenceBackend) | Base class for inference server backend implementations. |
### API
```python
class nemo_curator.core.serve.base.BaseModelConfig(
model_identifier: str,
model_name: str | None = None,
runtime_env: dict[str, typing.Any] = dict()
)
```
Dataclass
Base public model config shared by inference backends.
```python
nemo_curator.core.serve.base.BaseModelConfig._merge_package_runtime_env(
key: str,
base: dict[str, typing.Any] | list[str] | None,
override: dict[str, typing.Any] | list[str] | None
) -> dict[str, typing.Any] | list[str]
```
staticmethod
```python
nemo_curator.core.serve.base.BaseModelConfig.merge_runtime_envs(
base: dict[str, typing.Any],
override: dict[str, typing.Any] | None
) -> dict[str, typing.Any]
```
staticmethod
Merge two runtime\_env dicts while preserving package lists.
```python
class nemo_curator.core.serve.base.BaseServerConfig()
```
Dataclass
Base server-level config; subclasses declare which model config types they accept.
```python
class nemo_curator.core.serve.base.InferenceBackend()
```
Abstract
Base class for inference server backend implementations.
```python
nemo_curator.core.serve.base.InferenceBackend.start() -> None
```
abstract
```python
nemo_curator.core.serve.base.InferenceBackend.stop() -> None
```
abstract