# `vllm_mlx.models.llm`

MLX Language Model wrapper.

[View the complete module source at #L1-L422](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/llm.py#L1-L422).

## API details

Each callable below includes its exact signature, type annotations, inputs, defaults, return contract, documented exceptions, implementation source, and parsed docstring sections when the source provides them.

::: vllm_mlx.models.llm
    options:
      members:
        - logger
        - GenerationOutput
        - StreamingOutput
        - MLXLanguageModel
      filters: []
      show_if_no_docstring: true

## Complete contract reference

Expand any definition for its exact inputs, annotations, defaults, return contract, directly raised exceptions, source-grounded behavior, and immutable line link. This section includes private and nested definitions that ordinary API generators omit.

<details class="api-contract" id="contract-vllm_mlx.models.llm.GenerationOutput" markdown="1">
<summary><code>vllm_mlx.models.llm.GenerationOutput</code> · class</summary>

```python
vllm_mlx.models.llm.GenerationOutput(text: str, tokens: list[int], finish_reason: str | None = None)
```

Output from text generation.

**Parameters**

| Name | Type | Required | Default | Description |
| --- | --- | --- | --- | --- |
| `text` | `str` | `yes` | `none` | Required constructor field. |
| `tokens` | `list[int]` | `yes` | `none` | Required constructor field. |
| `finish_reason` | `str \| None` | `no` | `None` | Optional constructor field; defaults to `None`. |

**Returns**

- Constructs: `vllm_mlx.models.llm.GenerationOutput`

**Exceptions and behavior**

Class `GenerationOutput` declares 0 direct member(s).
No direct `raise` statement appears in this definition.

[View source #L21-L26](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/llm.py#L21-L26).

</details>

<details class="api-contract" id="contract-vllm_mlx.models.llm.StreamingOutput" markdown="1">
<summary><code>vllm_mlx.models.llm.StreamingOutput</code> · class</summary>

```python
vllm_mlx.models.llm.StreamingOutput(text: str, token: int, finished: bool = False, finish_reason: str | None = None, prompt_tokens: int = 0)
```

Streaming output chunk.

**Parameters**

| Name | Type | Required | Default | Description |
| --- | --- | --- | --- | --- |
| `text` | `str` | `yes` | `none` | Required constructor field. |
| `token` | `int` | `yes` | `none` | Required constructor field. |
| `finished` | `bool` | `no` | `False` | Optional constructor field; defaults to `False`. |
| `finish_reason` | `str \| None` | `no` | `None` | Optional constructor field; defaults to `None`. |
| `prompt_tokens` | `int` | `no` | `0` | Optional constructor field; defaults to `0`. |

**Returns**

- Constructs: `vllm_mlx.models.llm.StreamingOutput`

**Exceptions and behavior**

Class `StreamingOutput` declares 0 direct member(s).
No direct `raise` statement appears in this definition.

[View source #L30-L37](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/llm.py#L30-L37).

</details>

<details class="api-contract" id="contract-vllm_mlx.models.llm.MLXLanguageModel" markdown="1">
<summary><code>vllm_mlx.models.llm.MLXLanguageModel</code> · class</summary>

```python
vllm_mlx.models.llm.MLXLanguageModel(model_name: str, tokenizer_name: str | None = None, trust_remote_code: bool = False, mtp: bool = False, mtp_num_draft_tokens: int = 1)
```

Wrapper around mlx-lm for LLM inference.

**Parameters**

| Name | Type | Required | Default | Description |
| --- | --- | --- | --- | --- |
| `model_name` | `str` | `yes` | `none` | HuggingFace model name or local path |
| `tokenizer_name` | `str \| None` | `no` | `None` | Optional separate tokenizer name |
| `trust_remote_code` | `bool` | `no` | `False` | Whether to trust remote code |
| `mtp` | `bool` | `no` | `False` | Enable native MTP speculative decoding (model must have MTP head) |
| `mtp_num_draft_tokens` | `int` | `no` | `1` | Draft tokens per speculative MTP step |

**Returns**

- Constructs: `vllm_mlx.models.llm.MLXLanguageModel`

**Exceptions and behavior**

Class `MLXLanguageModel` declares 9 direct member(s).
No direct `raise` statement appears in this definition.

[View source #L40-L422](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/llm.py#L40-L422).

</details>

<details class="api-contract" id="contract-vllm_mlx.models.llm.MLXLanguageModel.__init__" markdown="1">
<summary><code>vllm_mlx.models.llm.MLXLanguageModel.__init__</code> · method</summary>

```python
vllm_mlx.models.llm.MLXLanguageModel.__init__(model_name: str, tokenizer_name: str | None = None, trust_remote_code: bool = False, mtp: bool = False, mtp_num_draft_tokens: int = 1) -> not annotated
```

Initialize the MLX language model.

**Parameters**

| Name | Type | Required | Default | Description |
| --- | --- | --- | --- | --- |
| `model_name` | `str` | `yes` | `none` | HuggingFace model name or local path |
| `tokenizer_name` | `str \| None` | `no` | `None` | Optional separate tokenizer name |
| `trust_remote_code` | `bool` | `no` | `False` | Whether to trust remote code |
| `mtp` | `bool` | `no` | `False` | Enable native MTP speculative decoding (model must have MTP head) |
| `mtp_num_draft_tokens` | `int` | `no` | `1` | Draft tokens per speculative MTP step |

**Returns**

- Type: `not annotated`

**Exceptions and behavior**

Method `MLXLanguageModel.__init__` updates `self.model_name`, `self.tokenizer_name`, `self.trust_remote_code`, `self._mtp`.
No direct `raise` statement appears in this definition.

[View source #L53-L79](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/llm.py#L53-L79).

</details>

<details class="api-contract" id="contract-vllm_mlx.models.llm.MLXLanguageModel.load" markdown="1">
<summary><code>vllm_mlx.models.llm.MLXLanguageModel.load</code> · method</summary>

```python
vllm_mlx.models.llm.MLXLanguageModel.load() -> None
```

Load the model and tokenizer.

**Parameters**

This callable has no explicit inputs.

**Returns**

- Type: `None`
- Direct return expressions: `None`

**Exceptions and behavior**

Method `MLXLanguageModel.load` updates `self.model`, `self.tokenizer`, `self._loaded`; calls `logger.info`, `self.model_name.lower`, `load_model_with_fallback`, `ImportError`; can raise `ImportError`; returns `None`.
Directly raised exceptions: `ImportError`.

[View source #L81-L114](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/llm.py#L81-L114).

</details>

<details class="api-contract" id="contract-vllm_mlx.models.llm.MLXLanguageModel._create_sampler" markdown="1">
<summary><code>vllm_mlx.models.llm.MLXLanguageModel._create_sampler</code> · method</summary>

```python
vllm_mlx.models.llm.MLXLanguageModel._create_sampler(temperature: float = 0.7, top_p: float = 0.9, top_k: int = 0, min_p: float = 0.0) -> not annotated
```

Create a sampler for text generation.

**Parameters**

| Name | Type | Required | Default | Description |
| --- | --- | --- | --- | --- |
| `temperature` | `float` | `no` | `0.7` | Optional positional or keyword input; defaults to `0.7`. |
| `top_p` | `float` | `no` | `0.9` | Optional positional or keyword input; defaults to `0.9`. |
| `top_k` | `int` | `no` | `0` | Optional positional or keyword input; defaults to `0`. |
| `min_p` | `float` | `no` | `0.0` | Optional positional or keyword input; defaults to `0.0`. |

**Returns**

- Type: `not annotated`
- Direct return expressions: `make_sampler(temp=temperature, top_p=top_p, top_k=top_k, min_p=min_p)`

**Exceptions and behavior**

Method `MLXLanguageModel._create_sampler` calls `make_sampler`; returns `make_sampler(temp=temperature, top_p=top_p, top_k=top_k, min_p=min_p)`.
No direct `raise` statement appears in this definition.

[View source #L116-L131](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/llm.py#L116-L131).

</details>

<details class="api-contract" id="contract-vllm_mlx.models.llm.MLXLanguageModel._create_logits_processors" markdown="1">
<summary><code>vllm_mlx.models.llm.MLXLanguageModel._create_logits_processors</code> · method</summary>

```python
vllm_mlx.models.llm.MLXLanguageModel._create_logits_processors(presence_penalty: float = 0.0, repetition_penalty: float = 1.0) -> not annotated
```

Create logits processors for penalty-based sampling.

**Parameters**

| Name | Type | Required | Default | Description |
| --- | --- | --- | --- | --- |
| `presence_penalty` | `float` | `no` | `0.0` | Optional positional or keyword input; defaults to `0.0`. |
| `repetition_penalty` | `float` | `no` | `1.0` | Optional positional or keyword input; defaults to `1.0`. |

**Returns**

- Type: `not annotated`
- Direct return expressions: `processors if processors else None`

**Exceptions and behavior**

Method `MLXLanguageModel._create_logits_processors` calls `make_logits_processors`; returns `processors if processors else None`.
No direct `raise` statement appears in this definition.

[View source #L133-L147](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/llm.py#L133-L147).

</details>

<details class="api-contract" id="contract-vllm_mlx.models.llm.MLXLanguageModel.generate" markdown="1">
<summary><code>vllm_mlx.models.llm.MLXLanguageModel.generate</code> · method</summary>

```python
vllm_mlx.models.llm.MLXLanguageModel.generate(prompt: str, max_tokens: int = 256, temperature: float = 0.7, top_p: float = 0.9, top_k: int = 0, min_p: float = 0.0, presence_penalty: float = 0.0, repetition_penalty: float = 1.0, stop: list[str] | None = None, logits_processors: list | None = None, **kwargs) -> GenerationOutput
```

Generate text from a prompt.

**Parameters**

| Name | Type | Required | Default | Description |
| --- | --- | --- | --- | --- |
| `prompt` | `str` | `yes` | `none` | Input prompt text |
| `max_tokens` | `int` | `no` | `256` | Maximum number of tokens to generate |
| `temperature` | `float` | `no` | `0.7` | Sampling temperature (0 = greedy) |
| `top_p` | `float` | `no` | `0.9` | Top-p (nucleus) sampling parameter |
| `top_k` | `int` | `no` | `0` | Top-k sampling (0 = disabled) |
| `min_p` | `float` | `no` | `0.0` | Minimum probability threshold |
| `presence_penalty` | `float` | `no` | `0.0` | Additive penalty for token presence |
| `repetition_penalty` | `float` | `no` | `1.0` | Multiplicative penalty for repeating tokens |
| `stop` | `list[str] \| None` | `no` | `None` | List of stop sequences |
| `logits_processors` | `list \| None` | `no` | `None` | Optional externally-supplied logits processors (e.g. JSON schema constrained decoding). Merged with built-in penalty processors. |
| `**kwargs` | `not annotated` | `no` | `none` | Additional variadic keyword inputs accepted by this callable. |

**Returns**

- Type: `GenerationOutput`
- Direct return expressions: `GenerationOutput(text=output_text, tokens=tokens, finish_reason=finish_reason)`

**Exceptions and behavior**

Method `MLXLanguageModel.generate` calls `self.load`, `self._create_sampler`, `self._create_logits_processors`, `list`; returns `GenerationOutput(text=output_text, tokens=tokens, finish_reason=finish_reason)`.
No direct `raise` statement appears in this definition.

[View source #L149-L219](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/llm.py#L149-L219).

</details>

<details class="api-contract" id="contract-vllm_mlx.models.llm.MLXLanguageModel.stream_generate" markdown="1">
<summary><code>vllm_mlx.models.llm.MLXLanguageModel.stream_generate</code> · method</summary>

```python
vllm_mlx.models.llm.MLXLanguageModel.stream_generate(prompt: Union[str, 'mx.array', list[int]], max_tokens: int = 256, temperature: float = 0.7, top_p: float = 0.9, top_k: int = 0, min_p: float = 0.0, presence_penalty: float = 0.0, repetition_penalty: float = 1.0, stop: list[str] | None = None, logits_processors: list | None = None, prompt_cache = None, **kwargs) -> Iterator[StreamingOutput]
```

Stream text generation token by token.

**Parameters**

| Name | Type | Required | Default | Description |
| --- | --- | --- | --- | --- |
| `prompt` | `Union[str, 'mx.array', list[int]]` | `yes` | `none` | Input prompt text, token array, or token id list |
| `max_tokens` | `int` | `no` | `256` | Maximum number of tokens to generate |
| `temperature` | `float` | `no` | `0.7` | Sampling temperature (0 = greedy) |
| `top_p` | `float` | `no` | `0.9` | Top-p (nucleus) sampling parameter |
| `top_k` | `int` | `no` | `0` | Top-k sampling (0 = disabled) |
| `min_p` | `float` | `no` | `0.0` | Minimum probability threshold |
| `presence_penalty` | `float` | `no` | `0.0` | Additive penalty for token presence |
| `repetition_penalty` | `float` | `no` | `1.0` | Multiplicative penalty for repeating tokens |
| `stop` | `list[str] \| None` | `no` | `None` | List of stop sequences |
| `logits_processors` | `list \| None` | `no` | `None` | Optional positional or keyword input; defaults to `None`. |
| `prompt_cache` | `not annotated` | `no` | `None` | Pre-populated KV cache (e.g. from SpecPrefill) |
| `**kwargs` | `not annotated` | `no` | `none` | Additional variadic keyword inputs accepted by this callable. |

**Returns**

- Type: `Iterator[StreamingOutput]`
- Yields values incrementally.

**Exceptions and behavior**

Method `MLXLanguageModel.stream_generate` calls `self.load`, `self._create_sampler`, `self._create_logits_processors`, `isinstance`; yields values incrementally.
No direct `raise` statement appears in this definition.

[View source #L221-L325](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/llm.py#L221-L325).

</details>

<details class="api-contract" id="contract-vllm_mlx.models.llm.MLXLanguageModel.chat" markdown="1">
<summary><code>vllm_mlx.models.llm.MLXLanguageModel.chat</code> · method</summary>

```python
vllm_mlx.models.llm.MLXLanguageModel.chat(messages: list[dict], max_tokens: int = 256, temperature: float = 0.7, top_p: float = 0.9, tools: list | None = None, chat_template_kwargs: dict | None = None, **kwargs) -> GenerationOutput
```

Generate a chat response.

**Parameters**

| Name | Type | Required | Default | Description |
| --- | --- | --- | --- | --- |
| `messages` | `list[dict]` | `yes` | `none` | List of chat messages [{"role": "user", "content": "..."}] |
| `max_tokens` | `int` | `no` | `256` | Maximum tokens to generate |
| `temperature` | `float` | `no` | `0.7` | Sampling temperature |
| `top_p` | `float` | `no` | `0.9` | Top-p sampling parameter |
| `tools` | `list \| None` | `no` | `None` | Optional list of tools for function calling |
| `chat_template_kwargs` | `dict \| None` | `no` | `None` | Optional positional or keyword input; defaults to `None`. |
| `**kwargs` | `not annotated` | `no` | `none` | Additional generation parameters |

**Returns**

- Type: `GenerationOutput`
- Direct return expressions: `self.generate(prompt=prompt, max_tokens=max_tokens, temperature=temperature, top_p=top_p, **kwargs)`

**Exceptions and behavior**

Method `MLXLanguageModel.chat` calls `self.load`, `hasattr`, `template_kwargs.update`, `self.tokenizer.apply_chat_template`; returns `self.generate(prompt=prompt, max_tokens=max_tokens, temperature=temperature, top_p=top_p, **kwargs)`.
No direct `raise` statement appears in this definition.

[View source #L327-L393](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/llm.py#L327-L393).

</details>

<details class="api-contract" id="contract-vllm_mlx.models.llm.MLXLanguageModel.get_model_info" markdown="1">
<summary><code>vllm_mlx.models.llm.MLXLanguageModel.get_model_info</code> · method</summary>

```python
vllm_mlx.models.llm.MLXLanguageModel.get_model_info() -> dict
```

Get information about the loaded model.

**Parameters**

This callable has no explicit inputs.

**Returns**

- Type: `dict`
- Direct return expressions: `{'loaded': False, 'model_name': self.model_name}`; `info`

**Exceptions and behavior**

Method `MLXLanguageModel.get_model_info` calls `hasattr`, `info.update`, `getattr`; has 2 explicit return paths.
No direct `raise` statement appears in this definition.

[View source #L395-L418](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/llm.py#L395-L418).

</details>

<details class="api-contract" id="contract-vllm_mlx.models.llm.MLXLanguageModel.__repr__" markdown="1">
<summary><code>vllm_mlx.models.llm.MLXLanguageModel.__repr__</code> · method</summary>

```python
vllm_mlx.models.llm.MLXLanguageModel.__repr__() -> str
```

Method `MLXLanguageModel.__repr__` returns `f'<MLXLanguageModel model={self.model_name} status={status}>'`.

**Parameters**

This callable has no explicit inputs.

**Returns**

- Type: `str`
- Direct return expressions: `f'<MLXLanguageModel model={self.model_name} status={status}>'`

**Exceptions and behavior**

Method `MLXLanguageModel.__repr__` returns `f'<MLXLanguageModel model={self.model_name} status={status}>'`.
No direct `raise` statement appears in this definition.

[View source #L420-L422](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/llm.py#L420-L422).

</details>

## Complete symbol map

This map also includes private definitions and nested helpers. The signature column exposes every explicit input even when an internal helper has no dedicated parameter prose.

| Symbol | Kind | Signature and inputs | What it does | Source |
| --- | --- | --- | --- | --- |
| [`GenerationOutput`](#contract-vllm_mlx.models.llm.GenerationOutput) | class | `GenerationOutput(text: str, tokens: list[int], finish_reason: str \| None = None)` | Output from text generation. | [#L21-L26](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/llm.py#L21-L26) |
| [`StreamingOutput`](#contract-vllm_mlx.models.llm.StreamingOutput) | class | `StreamingOutput(text: str, token: int, finished: bool = False, finish_reason: str \| None = None, prompt_tokens: int = 0)` | Streaming output chunk. | [#L30-L37](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/llm.py#L30-L37) |
| [`MLXLanguageModel`](#contract-vllm_mlx.models.llm.MLXLanguageModel) | class | `MLXLanguageModel(model_name: str, tokenizer_name: str \| None = None, trust_remote_code: bool = False, mtp: bool = False, mtp_num_draft_tokens: int = 1)` | Wrapper around mlx-lm for LLM inference. | [#L40-L422](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/llm.py#L40-L422) |
| [`MLXLanguageModel.__init__`](#contract-vllm_mlx.models.llm.MLXLanguageModel.__init__) | method | `MLXLanguageModel.__init__(model_name: str, tokenizer_name: str \| None = None, trust_remote_code: bool = False, mtp: bool = False, mtp_num_draft_tokens: int = 1) -> not annotated` | Initialize the MLX language model. | [#L53-L79](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/llm.py#L53-L79) |
| [`MLXLanguageModel.load`](#contract-vllm_mlx.models.llm.MLXLanguageModel.load) | method | `MLXLanguageModel.load() -> None` | Load the model and tokenizer. | [#L81-L114](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/llm.py#L81-L114) |
| [`MLXLanguageModel._create_sampler`](#contract-vllm_mlx.models.llm.MLXLanguageModel._create_sampler) | method | `MLXLanguageModel._create_sampler(temperature: float = 0.7, top_p: float = 0.9, top_k: int = 0, min_p: float = 0.0) -> not annotated` | Create a sampler for text generation. | [#L116-L131](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/llm.py#L116-L131) |
| [`MLXLanguageModel._create_logits_processors`](#contract-vllm_mlx.models.llm.MLXLanguageModel._create_logits_processors) | method | `MLXLanguageModel._create_logits_processors(presence_penalty: float = 0.0, repetition_penalty: float = 1.0) -> not annotated` | Create logits processors for penalty-based sampling. | [#L133-L147](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/llm.py#L133-L147) |
| [`MLXLanguageModel.generate`](#contract-vllm_mlx.models.llm.MLXLanguageModel.generate) | method | `MLXLanguageModel.generate(prompt: str, max_tokens: int = 256, temperature: float = 0.7, top_p: float = 0.9, top_k: int = 0, min_p: float = 0.0, presence_penalty: float = 0.0, repetition_penalty: float = 1.0, stop: list[str] \| None = None, logits_processors: list \| None = None, **kwargs) -> GenerationOutput` | Generate text from a prompt. | [#L149-L219](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/llm.py#L149-L219) |
| [`MLXLanguageModel.stream_generate`](#contract-vllm_mlx.models.llm.MLXLanguageModel.stream_generate) | method | `MLXLanguageModel.stream_generate(prompt: Union[str, 'mx.array', list[int]], max_tokens: int = 256, temperature: float = 0.7, top_p: float = 0.9, top_k: int = 0, min_p: float = 0.0, presence_penalty: float = 0.0, repetition_penalty: float = 1.0, stop: list[str] \| None = None, logits_processors: list \| None = None, prompt_cache = None, **kwargs) -> Iterator[StreamingOutput]` | Stream text generation token by token. | [#L221-L325](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/llm.py#L221-L325) |
| [`MLXLanguageModel.chat`](#contract-vllm_mlx.models.llm.MLXLanguageModel.chat) | method | `MLXLanguageModel.chat(messages: list[dict], max_tokens: int = 256, temperature: float = 0.7, top_p: float = 0.9, tools: list \| None = None, chat_template_kwargs: dict \| None = None, **kwargs) -> GenerationOutput` | Generate a chat response. | [#L327-L393](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/llm.py#L327-L393) |
| [`MLXLanguageModel.get_model_info`](#contract-vllm_mlx.models.llm.MLXLanguageModel.get_model_info) | method | `MLXLanguageModel.get_model_info() -> dict` | Get information about the loaded model. | [#L395-L418](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/llm.py#L395-L418) |
| [`MLXLanguageModel.__repr__`](#contract-vllm_mlx.models.llm.MLXLanguageModel.__repr__) | method | `MLXLanguageModel.__repr__() -> str` | Method `MLXLanguageModel.__repr__` returns `f'<MLXLanguageModel model={self.model_name} status={status}>'`. | [#L420-L422](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/llm.py#L420-L422) |