# `vllm_mlx.models.mllm` MLX Multimodal Language Model (MLLM) wrapper. [View the complete module source at #L1-L2944](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L1-L2944). ## 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.mllm options: members: - logger - TempFileManager - _temp_manager - cleanup_temp_file - cleanup_all_temp_files - FRAME_FACTOR - DEFAULT_FPS - MIN_FRAMES - MAX_FRAMES - IMAGE_FACTOR - MAX_IMAGE_SIZE - MAX_VIDEO_SIZE - MAX_AUDIO_SIZE - MAX_BASE64_IMAGE_LENGTH - MAX_BASE64_VIDEO_LENGTH - MAX_BASE64_AUDIO_LENGTH - FileSizeExceededError - UnsafeRemoteURLError - _normalize_content_part - _extract_media_url - _text_content_part - _append_text_content_part - _build_string_mllm_message_content - _append_ordered_mllm_content_part - _build_ordered_mllm_message_content - _normalize_mllm_tool_calls - _build_mllm_chat_messages - MultimodalInput - MLLMOutput - load_gemma4_assistant_drafter - _DRAFT_KWARG_NAMES - _count_draft_tokens - _install_draft_metrics_hooks - is_base64_image - is_url - is_base64_video - is_base64_audio - decode_base64_image - _validate_url_safety - _request_with_safe_redirects - download_image - _VIDEO_EXT_MAP - _AUDIO_EXT_MAP - _download_media - download_video - download_audio - decode_base64_video - decode_base64_audio - process_video_input - process_audio_input - _video_has_audio_track - _model_has_sound_encoder - extract_audio_from_video - _base64_image_cache - save_base64_image - process_image_input - round_by_factor - ceil_by_factor - floor_by_factor - smart_nframes - extract_video_frames_smart - save_frames_to_temp - MLXMultimodalLM - MLXVisionLanguageModel - VLMOutput - is_vlm_model 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.
vllm_mlx.models.mllm.TempFileManager · class ```python vllm_mlx.models.mllm.TempFileManager() ``` Thread-safe manager for tracking and cleaning up temporary files. **Parameters** This callable has no explicit inputs. **Returns** - Constructs: `vllm_mlx.models.mllm.TempFileManager` **Exceptions and behavior** Class `TempFileManager` declares 4 direct member(s). No direct `raise` statement appears in this definition. [View source #L41-L86](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L41-L86).
vllm_mlx.models.mllm.TempFileManager.__init__ · method ```python vllm_mlx.models.mllm.TempFileManager.__init__() -> not annotated ``` Method `TempFileManager.__init__` updates `self._files`, `self._lock`; calls `set`, `threading.Lock`, `atexit.register`. **Parameters** This callable has no explicit inputs. **Returns** - Type: `not annotated` **Exceptions and behavior** Method `TempFileManager.__init__` updates `self._files`, `self._lock`; calls `set`, `threading.Lock`, `atexit.register`. No direct `raise` statement appears in this definition. [View source #L44-L47](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L44-L47).
vllm_mlx.models.mllm.TempFileManager.register · method ```python vllm_mlx.models.mllm.TempFileManager.register(path: str) -> str ``` Register a temp file for tracking. **Parameters** | Name | Type | Required | Default | Description | | --- | --- | --- | --- | --- | | `path` | `str` | `yes` | `none` | Required positional or keyword input. | **Returns** - Type: `str` - Direct return expressions: `path` **Exceptions and behavior** Method `TempFileManager.register` calls `self._files.add`; returns `path`. No direct `raise` statement appears in this definition. [View source #L49-L53](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L49-L53).
vllm_mlx.models.mllm.TempFileManager.cleanup · method ```python vllm_mlx.models.mllm.TempFileManager.cleanup(path: str) -> bool ``` Clean up a specific temp file. **Parameters** | Name | Type | Required | Default | Description | | --- | --- | --- | --- | --- | | `path` | `str` | `yes` | `none` | Required positional or keyword input. | **Returns** - Type: `bool` - Direct return expressions: `True`; `False` **Exceptions and behavior** Method `TempFileManager.cleanup` calls `self._files.discard`, `os.path.exists`, `os.unlink`, `logger.debug`; has 2 explicit return paths. No direct `raise` statement appears in this definition. [View source #L55-L67](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L55-L67).
vllm_mlx.models.mllm.TempFileManager.cleanup_all · method ```python vllm_mlx.models.mllm.TempFileManager.cleanup_all() -> int ``` Clean up all tracked temp files. **Parameters** This callable has no explicit inputs. **Returns** - Type: `int` - Direct return expressions: `cleaned` **Exceptions and behavior** Method `TempFileManager.cleanup_all` calls `list`, `self._files.clear`, `os.path.exists`, `os.unlink`; returns `cleaned`. No direct `raise` statement appears in this definition. [View source #L69-L86](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L69-L86).
vllm_mlx.models.mllm.cleanup_temp_file · function ```python vllm_mlx.models.mllm.cleanup_temp_file(path: str) -> bool ``` Clean up a specific temporary file. **Parameters** | Name | Type | Required | Default | Description | | --- | --- | --- | --- | --- | | `path` | `str` | `yes` | `none` | Required positional or keyword input. | **Returns** - Type: `bool` - Direct return expressions: `_temp_manager.cleanup(path)` **Exceptions and behavior** Function `cleanup_temp_file` calls `_temp_manager.cleanup`; returns `_temp_manager.cleanup(path)`. No direct `raise` statement appears in this definition. [View source #L93-L95](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L93-L95).
vllm_mlx.models.mllm.cleanup_all_temp_files · function ```python vllm_mlx.models.mllm.cleanup_all_temp_files() -> int ``` Clean up all tracked temporary files. **Parameters** This callable has no explicit inputs. **Returns** - Type: `int` - Direct return expressions: `_temp_manager.cleanup_all()` **Exceptions and behavior** Function `cleanup_all_temp_files` calls `_temp_manager.cleanup_all`; returns `_temp_manager.cleanup_all()`. No direct `raise` statement appears in this definition. [View source #L98-L100](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L98-L100).
vllm_mlx.models.mllm.FileSizeExceededError · class ```python vllm_mlx.models.mllm.FileSizeExceededError() ``` Raised when a downloaded file exceeds the size limit. **Parameters** This callable has no explicit inputs. **Returns** - Constructs: `vllm_mlx.models.mllm.FileSizeExceededError` **Exceptions and behavior** Class `FileSizeExceededError` derives from `Exception` and declares 0 direct member(s). No direct `raise` statement appears in this definition. [View source #L119-L122](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L119-L122).
vllm_mlx.models.mllm.UnsafeRemoteURLError · class ```python vllm_mlx.models.mllm.UnsafeRemoteURLError(message: str, *, public_message: str = 'Remote media URL is not allowed') ``` Raised when a remote media URL targets an unsafe destination. **Parameters** | Name | Type | Required | Default | Description | | --- | --- | --- | --- | --- | | `message` | `str` | `yes` | `none` | Required positional or keyword input. | | `public_message` | `str` | `no` | `'Remote media URL is not allowed'` | Optional keyword-only input; defaults to `'Remote media URL is not allowed'`. | **Returns** - Constructs: `vllm_mlx.models.mllm.UnsafeRemoteURLError` **Exceptions and behavior** Class `UnsafeRemoteURLError` derives from `ValueError` and declares 1 direct member(s). No direct `raise` statement appears in this definition. [View source #L125-L135](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L125-L135).
vllm_mlx.models.mllm.UnsafeRemoteURLError.__init__ · method ```python vllm_mlx.models.mllm.UnsafeRemoteURLError.__init__(message: str, *, public_message: str = 'Remote media URL is not allowed') -> None ``` Method `UnsafeRemoteURLError.__init__` updates `self.public_message`; calls `super().__init__`, `super`. **Parameters** | Name | Type | Required | Default | Description | | --- | --- | --- | --- | --- | | `message` | `str` | `yes` | `none` | Required positional or keyword input. | | `public_message` | `str` | `no` | `'Remote media URL is not allowed'` | Optional keyword-only input; defaults to `'Remote media URL is not allowed'`. | **Returns** - Type: `None` **Exceptions and behavior** Method `UnsafeRemoteURLError.__init__` updates `self.public_message`; calls `super().__init__`, `super`. No direct `raise` statement appears in this definition. [View source #L128-L135](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L128-L135).
vllm_mlx.models.mllm._normalize_content_part · function ```python vllm_mlx.models.mllm._normalize_content_part(item: object) -> object ``` Convert Pydantic content parts into plain Python objects. **Parameters** | Name | Type | Required | Default | Description | | --- | --- | --- | --- | --- | | `item` | `object` | `yes` | `none` | Required positional or keyword input. | **Returns** - Type: `object` - Direct return expressions: `item.model_dump(exclude_none=True)`; `{k: v for k, v in item.dict().items() if v is not None}`; `item` **Exceptions and behavior** Function `_normalize_content_part` calls `hasattr`, `item.model_dump`, `item.dict().items`, `item.dict`; has 3 explicit return paths. No direct `raise` statement appears in this definition. [View source #L138-L144](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L138-L144).
vllm_mlx.models.mllm._extract_media_url · function ```python vllm_mlx.models.mllm._extract_media_url(item: dict, item_type: str) -> str ``` Function `_extract_media_url` calls `item.get`, `isinstance`, `media_value.get`; has 2 explicit return paths. **Parameters** | Name | Type | Required | Default | Description | | --- | --- | --- | --- | --- | | `item` | `dict` | `yes` | `none` | Required positional or keyword input. | | `item_type` | `str` | `yes` | `none` | Required positional or keyword input. | **Returns** - Type: `str` - Direct return expressions: `''`; `media_value if isinstance(media_value, str) else ''` **Exceptions and behavior** Function `_extract_media_url` calls `item.get`, `isinstance`, `media_value.get`; has 2 explicit return paths. No direct `raise` statement appears in this definition. [View source #L147-L161](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L147-L161).
vllm_mlx.models.mllm._text_content_part · function ```python vllm_mlx.models.mllm._text_content_part(text: str) -> dict[str, str] ``` Function `_text_content_part` returns `{'type': 'text', 'text': text, 'content': text}`. **Parameters** | Name | Type | Required | Default | Description | | --- | --- | --- | --- | --- | | `text` | `str` | `yes` | `none` | Required positional or keyword input. | **Returns** - Type: `dict[str, str]` - Direct return expressions: `{'type': 'text', 'text': text, 'content': text}` **Exceptions and behavior** Function `_text_content_part` returns `{'type': 'text', 'text': text, 'content': text}`. No direct `raise` statement appears in this definition. [View source #L164-L165](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L164-L165).
vllm_mlx.models.mllm._append_text_content_part · function ```python vllm_mlx.models.mllm._append_text_content_part(built_parts: list[dict[str, str]], text_parts: list[str], text: str) -> None ``` Function `_append_text_content_part` calls `built_parts.append`, `_text_content_part`, `text_parts.append`; returns `None`. **Parameters** | Name | Type | Required | Default | Description | | --- | --- | --- | --- | --- | | `built_parts` | `list[dict[str, str]]` | `yes` | `none` | Required positional or keyword input. | | `text_parts` | `list[str]` | `yes` | `none` | Required positional or keyword input. | | `text` | `str` | `yes` | `none` | Required positional or keyword input. | **Returns** - Type: `None` - Direct return expressions: `None` **Exceptions and behavior** Function `_append_text_content_part` calls `built_parts.append`, `_text_content_part`, `text_parts.append`; returns `None`. No direct `raise` statement appears in this definition. [View source #L168-L174](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L168-L174).
vllm_mlx.models.mllm._build_string_mllm_message_content · function ```python vllm_mlx.models.mllm._build_string_mllm_message_content(content: str, role: str) -> tuple[object, bool] ``` Function `_build_string_mllm_message_content` calls `_text_content_part`; has 3 explicit return paths. **Parameters** | Name | Type | Required | Default | Description | | --- | --- | --- | --- | --- | | `content` | `str` | `yes` | `none` | Required positional or keyword input. | | `role` | `str` | `yes` | `none` | Required positional or keyword input. | **Returns** - Type: `tuple[object, bool]` - Direct return expressions: `('', False)`; `(content, True)`; `([_text_content_part(content)], True)` **Exceptions and behavior** Function `_build_string_mllm_message_content` calls `_text_content_part`; has 3 explicit return paths. No direct `raise` statement appears in this definition. [View source #L177-L182](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L177-L182).
vllm_mlx.models.mllm._append_ordered_mllm_content_part · function ```python vllm_mlx.models.mllm._append_ordered_mllm_content_part(raw_item: object, *, built_parts: list[dict[str, str]], text_parts: list[str], all_image_urls: list[str], video_frame_count: int) -> int ``` Function `_append_ordered_mllm_content_part` calls `_normalize_content_part`, `isinstance`, `_append_text_content_part`, `item.get`; has 2 explicit return paths. **Parameters** | Name | Type | Required | Default | Description | | --- | --- | --- | --- | --- | | `raw_item` | `object` | `yes` | `none` | Required positional or keyword input. | | `built_parts` | `list[dict[str, str]]` | `yes` | `none` | Required keyword-only input. | | `text_parts` | `list[str]` | `yes` | `none` | Required keyword-only input. | | `all_image_urls` | `list[str]` | `yes` | `none` | Required keyword-only input. | | `video_frame_count` | `int` | `yes` | `none` | Required keyword-only input. | **Returns** - Type: `int` - Direct return expressions: `video_frame_count`; `0` **Exceptions and behavior** Function `_append_ordered_mllm_content_part` calls `_normalize_content_part`, `isinstance`, `_append_text_content_part`, `item.get`; has 2 explicit return paths. No direct `raise` statement appears in this definition. [View source #L185-L220](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L185-L220).
vllm_mlx.models.mllm._build_ordered_mllm_message_content · function ```python vllm_mlx.models.mllm._build_ordered_mllm_message_content(content: object, *, role: str, all_image_urls: list[str], video_frame_count: int = 0) -> tuple[object, bool] ``` Build template content while preserving OpenAI media/text part order. **Parameters** | Name | Type | Required | Default | Description | | --- | --- | --- | --- | --- | | `content` | `object` | `yes` | `none` | Required positional or keyword input. | | `role` | `str` | `yes` | `none` | Required keyword-only input. | | `all_image_urls` | `list[str]` | `yes` | `none` | Required keyword-only input. | | `video_frame_count` | `int` | `no` | `0` | Optional keyword-only input; defaults to `0`. | **Returns** - Type: `tuple[object, bool]` - Direct return expressions: `_build_string_mllm_message_content(content, role)`; `('', False)`; `(text, bool(text))`; `(built_parts, bool(built_parts))` **Exceptions and behavior** Function `_build_ordered_mllm_message_content` calls `isinstance`, `_build_string_mllm_message_content`, `_append_ordered_mllm_content_part`, `''.join`; has 4 explicit return paths. No direct `raise` statement appears in this definition. [View source #L223-L254](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L223-L254).
vllm_mlx.models.mllm._normalize_mllm_tool_calls · function ```python vllm_mlx.models.mllm._normalize_mllm_tool_calls(tool_calls: list) -> list ``` Normalize replayed assistant tool calls for chat templates. **Parameters** | Name | Type | Required | Default | Description | | --- | --- | --- | --- | --- | | `tool_calls` | `list` | `yes` | `none` | Required positional or keyword input. | **Returns** - Type: `list` - Direct return expressions: `normalized[0].get('tool_calls', plain_calls)` **Exceptions and behavior** Function `_normalize_mllm_tool_calls` calls `_normalize_content_part`, `normalize_messages_for_chat_template`, `normalized[0].get`; returns `normalized[0].get('tool_calls', plain_calls)`. No direct `raise` statement appears in this definition. [View source #L257-L268](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L257-L268).
vllm_mlx.models.mllm._build_mllm_chat_messages · function ```python vllm_mlx.models.mllm._build_mllm_chat_messages(messages: list[dict], *, all_image_urls: list[str], video_frame_counts: dict[int, int]) -> list[dict] ``` Build chat-template messages without reordering multimodal content parts. **Parameters** | Name | Type | Required | Default | Description | | --- | --- | --- | --- | --- | | `messages` | `list[dict]` | `yes` | `none` | Required positional or keyword input. | | `all_image_urls` | `list[str]` | `yes` | `none` | Required keyword-only input. | | `video_frame_counts` | `dict[int, int]` | `yes` | `none` | Required keyword-only input. | **Returns** - Type: `list[dict]` - Direct return expressions: `chat_messages` **Exceptions and behavior** Function `_build_mllm_chat_messages` calls `enumerate`, `msg.get`, `isinstance`, `str`; returns `chat_messages`. No direct `raise` statement appears in this definition. [View source #L271-L315](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L271-L315).
vllm_mlx.models.mllm.MultimodalInput · class ```python vllm_mlx.models.mllm.MultimodalInput(prompt: str, images: list[str] = field(default_factory=list), videos: list[str] = field(default_factory=list), audio: list[str] = field(default_factory=list)) ``` Input for multimodal generation. **Parameters** | Name | Type | Required | Default | Description | | --- | --- | --- | --- | --- | | `prompt` | `str` | `yes` | `none` | Required constructor field. | | `images` | `list[str]` | `no` | `field(default_factory=list)` | Optional constructor field; defaults to `field(default_factory=list)`. | | `videos` | `list[str]` | `no` | `field(default_factory=list)` | Optional constructor field; defaults to `field(default_factory=list)`. | | `audio` | `list[str]` | `no` | `field(default_factory=list)` | Optional constructor field; defaults to `field(default_factory=list)`. | **Returns** - Constructs: `vllm_mlx.models.mllm.MultimodalInput` **Exceptions and behavior** Class `MultimodalInput` declares 0 direct member(s). No direct `raise` statement appears in this definition. [View source #L319-L325](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L319-L325).
vllm_mlx.models.mllm.MLLMOutput · class ```python vllm_mlx.models.mllm.MLLMOutput(text: str, finish_reason: str | None = None, prompt_tokens: int = 0, completion_tokens: int = 0, mtp_drafts: int = 0, mtp_accepted: int = 0) ``` Output from multimodal language model. **Parameters** | Name | Type | Required | Default | Description | | --- | --- | --- | --- | --- | | `text` | `str` | `yes` | `none` | Required constructor field. | | `finish_reason` | `str \| None` | `no` | `None` | Optional constructor field; defaults to `None`. | | `prompt_tokens` | `int` | `no` | `0` | Optional constructor field; defaults to `0`. | | `completion_tokens` | `int` | `no` | `0` | Optional constructor field; defaults to `0`. | | `mtp_drafts` | `int` | `no` | `0` | Optional constructor field; defaults to `0`. | | `mtp_accepted` | `int` | `no` | `0` | Optional constructor field; defaults to `0`. | **Returns** - Constructs: `vllm_mlx.models.mllm.MLLMOutput` **Exceptions and behavior** Class `MLLMOutput` declares 0 direct member(s). No direct `raise` statement appears in this definition. [View source #L329-L337](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L329-L337).
vllm_mlx.models.mllm.load_gemma4_assistant_drafter · function ```python vllm_mlx.models.mllm.load_gemma4_assistant_drafter(model_path: str) -> not annotated ``` Load a Gemma 4 assistant drafter for mlx-vlm speculative decoding. **Parameters** | Name | Type | Required | Default | Description | | --- | --- | --- | --- | --- | | `model_path` | `str` | `yes` | `none` | Required positional or keyword input. | **Returns** - Type: `not annotated` - Direct return expressions: `model` **Exceptions and behavior** Function `load_gemma4_assistant_drafter` calls `ImportError`, `version`, `logger.info`, `Path`; can raise `ImportError`, `FileNotFoundError`; returns `model`. Directly raised exceptions: `ImportError`, `FileNotFoundError`. [View source #L340-L381](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L340-L381).
vllm_mlx.models.mllm._count_draft_tokens · function ```python vllm_mlx.models.mllm._count_draft_tokens(draft_tokens) -> int ``` Best-effort drafted-token count for an mlx-vlm drafter output. **Parameters** | Name | Type | Required | Default | Description | | --- | --- | --- | --- | --- | | `draft_tokens` | `not annotated` | `yes` | `none` | Required positional or keyword input. | **Returns** - Type: `int` - Direct return expressions: `max(int(shape[-1]), 0)`; `max(len(draft_tokens), 0)`; `0` **Exceptions and behavior** Function `_count_draft_tokens` calls `getattr`, `max`, `int`, `len`; has 3 explicit return paths. No direct `raise` statement appears in this definition. [View source #L387-L398](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L387-L398).
vllm_mlx.models.mllm._install_draft_metrics_hooks · function ```python vllm_mlx.models.mllm._install_draft_metrics_hooks(draft_model) -> None ``` Record actual drafted token counts from mlx-vlm assistant drafters. **Parameters** | Name | Type | Required | Default | Description | | --- | --- | --- | --- | --- | | `draft_model` | `not annotated` | `yes` | `none` | Required positional or keyword input. | **Returns** - Type: `None` - Direct return expressions: `None` **Exceptions and behavior** Function `_install_draft_metrics_hooks` calls `getattr`, `hasattr`, `callable`; returns `None`. No direct `raise` statement appears in this definition. [View source #L401-L428](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L401-L428).
vllm_mlx.models.mllm._install_draft_metrics_hooks.draft_block_with_metrics · nested function ```python vllm_mlx.models.mllm._install_draft_metrics_hooks.draft_block_with_metrics(*args, **kwargs) -> not annotated ``` Nested Function `_install_draft_metrics_hooks.draft_block_with_metrics` calls `draft_block`, `draft_model._vllm_mlx_draft_counts.append`, `_count_draft_tokens`; returns `draft_tokens`. **Parameters** | Name | Type | Required | Default | Description | | --- | --- | --- | --- | --- | | `*args` | `not annotated` | `no` | `none` | Additional variadic positional inputs accepted by this callable. | | `**kwargs` | `not annotated` | `no` | `none` | Additional variadic keyword inputs accepted by this callable. | **Returns** - Type: `not annotated` - Direct return expressions: `draft_tokens` **Exceptions and behavior** Nested Function `_install_draft_metrics_hooks.draft_block_with_metrics` calls `draft_block`, `draft_model._vllm_mlx_draft_counts.append`, `_count_draft_tokens`; returns `draft_tokens`. No direct `raise` statement appears in this definition. [View source #L412-L415](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L412-L415).
vllm_mlx.models.mllm._install_draft_metrics_hooks.reset_with_metrics · nested function ```python vllm_mlx.models.mllm._install_draft_metrics_hooks.reset_with_metrics(*args, **kwargs) -> not annotated ``` Nested Function `_install_draft_metrics_hooks.reset_with_metrics` calls `reset`; returns `reset(*args, **kwargs)`. **Parameters** | Name | Type | Required | Default | Description | | --- | --- | --- | --- | --- | | `*args` | `not annotated` | `no` | `none` | Additional variadic positional inputs accepted by this callable. | | `**kwargs` | `not annotated` | `no` | `none` | Additional variadic keyword inputs accepted by this callable. | **Returns** - Type: `not annotated` - Direct return expressions: `reset(*args, **kwargs)` **Exceptions and behavior** Nested Function `_install_draft_metrics_hooks.reset_with_metrics` calls `reset`; returns `reset(*args, **kwargs)`. No direct `raise` statement appears in this definition. [View source #L422-L424](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L422-L424).
vllm_mlx.models.mllm.is_base64_image · function ```python vllm_mlx.models.mllm.is_base64_image(s: str) -> bool ``` Check if string is base64-encoded image data. **Parameters** | Name | Type | Required | Default | Description | | --- | --- | --- | --- | --- | | `s` | `str` | `yes` | `none` | Required positional or keyword input. | **Returns** - Type: `bool` - Direct return expressions: `s.startswith('data:image/') or (len(s) > 100 and (not s.startswith(('http://', 'https://', '/'))))` **Exceptions and behavior** Function `is_base64_image` calls `s.startswith`, `len`; returns `s.startswith('data:image/') or (len(s) > 100 and (not s.startswith(('http://', 'https://', '/'))))`. No direct `raise` statement appears in this definition. [View source #L431-L435](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L431-L435).
vllm_mlx.models.mllm.is_url · function ```python vllm_mlx.models.mllm.is_url(s: str) -> bool ``` Check if string is a URL. **Parameters** | Name | Type | Required | Default | Description | | --- | --- | --- | --- | --- | | `s` | `str` | `yes` | `none` | Required positional or keyword input. | **Returns** - Type: `bool` - Direct return expressions: `s.startswith(('http://', 'https://'))` **Exceptions and behavior** Function `is_url` calls `s.startswith`; returns `s.startswith(('http://', 'https://'))`. No direct `raise` statement appears in this definition. [View source #L438-L440](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L438-L440).
vllm_mlx.models.mllm.is_base64_video · function ```python vllm_mlx.models.mllm.is_base64_video(s: str) -> bool ``` Check if string is base64-encoded video data. **Parameters** | Name | Type | Required | Default | Description | | --- | --- | --- | --- | --- | | `s` | `str` | `yes` | `none` | Required positional or keyword input. | **Returns** - Type: `bool` - Direct return expressions: `s.startswith('data:video/')` **Exceptions and behavior** Function `is_base64_video` calls `s.startswith`; returns `s.startswith('data:video/')`. No direct `raise` statement appears in this definition. [View source #L443-L445](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L443-L445).
vllm_mlx.models.mllm.is_base64_audio · function ```python vllm_mlx.models.mllm.is_base64_audio(s: str) -> bool ``` Check if string is base64-encoded audio data. **Parameters** | Name | Type | Required | Default | Description | | --- | --- | --- | --- | --- | | `s` | `str` | `yes` | `none` | Required positional or keyword input. | **Returns** - Type: `bool` - Direct return expressions: `s.startswith('data:audio/')` **Exceptions and behavior** Function `is_base64_audio` calls `s.startswith`; returns `s.startswith('data:audio/')`. No direct `raise` statement appears in this definition. [View source #L448-L450](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L448-L450).
vllm_mlx.models.mllm.decode_base64_image · function ```python vllm_mlx.models.mllm.decode_base64_image(base64_string: str, max_length: int = MAX_BASE64_IMAGE_LENGTH) -> bytes ``` Decode base64 image to bytes. **Parameters** | Name | Type | Required | Default | Description | | --- | --- | --- | --- | --- | | `base64_string` | `str` | `yes` | `none` | Base64 encoded image (optionally with data URL prefix) | | `max_length` | `int` | `no` | `MAX_BASE64_IMAGE_LENGTH` | Maximum allowed length of base64 string | **Returns** - Type: `bytes` - Direct return expressions: `base64.b64decode(data)`; `base64.b64decode(base64_string)` **Exceptions and behavior** Function `decode_base64_image` calls `len`, `FileSizeExceededError`, `base64_string.startswith`, `base64_string.split`; can raise `FileSizeExceededError`; has 2 explicit return paths. Directly raised exceptions: `FileSizeExceededError`. [View source #L453-L480](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L453-L480).
vllm_mlx.models.mllm._validate_url_safety · function ```python vllm_mlx.models.mllm._validate_url_safety(url: str) -> None ``` Reject remote URLs that target local or private network resources. **Parameters** | Name | Type | Required | Default | Description | | --- | --- | --- | --- | --- | | `url` | `str` | `yes` | `none` | Required positional or keyword input. | **Returns** - Type: `None` **Exceptions and behavior** Function `_validate_url_safety` calls `urlparse`, `UnsafeRemoteURLError`, `hostname.endswith`, `ipaddress.ip_address`; can raise `UnsafeRemoteURLError`. Directly raised exceptions: `UnsafeRemoteURLError`. [View source #L483-L519](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L483-L519).
vllm_mlx.models.mllm._request_with_safe_redirects · function ```python vllm_mlx.models.mllm._request_with_safe_redirects(method: str, url: str, *, timeout: int, headers: dict[str, str], stream: bool = False, max_redirects: int = 5) -> not annotated ``` Issue a requests call while validating every redirect target. **Parameters** | Name | Type | Required | Default | Description | | --- | --- | --- | --- | --- | | `method` | `str` | `yes` | `none` | Required positional or keyword input. | | `url` | `str` | `yes` | `none` | Required positional or keyword input. | | `timeout` | `int` | `yes` | `none` | Required keyword-only input. | | `headers` | `dict[str, str]` | `yes` | `none` | Required keyword-only input. | | `stream` | `bool` | `no` | `False` | Optional keyword-only input; defaults to `False`. | | `max_redirects` | `int` | `no` | `5` | Optional keyword-only input; defaults to `5`. | **Returns** - Type: `not annotated` - Direct return expressions: `response` **Exceptions and behavior** Function `_request_with_safe_redirects` calls `range`, `_validate_url_safety`, `requests.request`, `response.headers.get`; can raise `UnsafeRemoteURLError`; returns `response`. Directly raised exceptions: `UnsafeRemoteURLError`. [View source #L522-L557](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L522-L557).
vllm_mlx.models.mllm.download_image · function ```python vllm_mlx.models.mllm.download_image(url: str, timeout: int = 30, max_size: int = MAX_IMAGE_SIZE) -> str ``` Download image from URL and return local path. **Parameters** | Name | Type | Required | Default | Description | | --- | --- | --- | --- | --- | | `url` | `str` | `yes` | `none` | Image URL | | `timeout` | `int` | `no` | `30` | Download timeout in seconds | | `max_size` | `int` | `no` | `MAX_IMAGE_SIZE` | Maximum allowed file size in bytes | **Returns** - Type: `str` - Direct return expressions: `_temp_manager.register(temp_file.name)` **Exceptions and behavior** Function `download_image` calls `_request_with_safe_redirects`, `head_response.headers.get`, `int`, `FileSizeExceededError`; can raise `FileSizeExceededError`; returns `_temp_manager.register(temp_file.name)`. Directly raised exceptions: `FileSizeExceededError`. [View source #L560-L645](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L560-L645).
vllm_mlx.models.mllm._download_media · function ```python vllm_mlx.models.mllm._download_media(url: str, media_type: str, ext_map: dict[str, str], default_ext: str, timeout: int, max_size: int) -> str ``` Download media from URL, enforce size limits, and return a local temp path. **Parameters** | Name | Type | Required | Default | Description | | --- | --- | --- | --- | --- | | `url` | `str` | `yes` | `none` | Required positional or keyword input. | | `media_type` | `str` | `yes` | `none` | Required positional or keyword input. | | `ext_map` | `dict[str, str]` | `yes` | `none` | Required positional or keyword input. | | `default_ext` | `str` | `yes` | `none` | Required positional or keyword input. | | `timeout` | `int` | `yes` | `none` | Required positional or keyword input. | | `max_size` | `int` | `yes` | `none` | Required positional or keyword input. | **Returns** - Type: `str` - Direct return expressions: `_temp_manager.register(temp_file.name)` **Exceptions and behavior** Function `_download_media` calls `logger.info`, `_request_with_safe_redirects`, `head_response.headers.get`, `int`; can raise `FileSizeExceededError`; returns `_temp_manager.register(temp_file.name)`. Directly raised exceptions: `FileSizeExceededError`. [View source #L670-L748](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L670-L748).
vllm_mlx.models.mllm.download_video · function ```python vllm_mlx.models.mllm.download_video(url: str, timeout: int = 120, max_size: int = MAX_VIDEO_SIZE) -> str ``` Download video from URL and return local path. **Parameters** | Name | Type | Required | Default | Description | | --- | --- | --- | --- | --- | | `url` | `str` | `yes` | `none` | Required positional or keyword input. | | `timeout` | `int` | `no` | `120` | Optional positional or keyword input; defaults to `120`. | | `max_size` | `int` | `no` | `MAX_VIDEO_SIZE` | Optional positional or keyword input; defaults to `MAX_VIDEO_SIZE`. | **Returns** - Type: `str` - Direct return expressions: `_download_media(url, 'video', _VIDEO_EXT_MAP, '.mp4', timeout, max_size)` **Exceptions and behavior** Function `download_video` calls `_download_media`; returns `_download_media(url, 'video', _VIDEO_EXT_MAP, '.mp4', timeout, max_size)`. No direct `raise` statement appears in this definition. [View source #L751-L753](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L751-L753).
vllm_mlx.models.mllm.download_audio · function ```python vllm_mlx.models.mllm.download_audio(url: str, timeout: int = 120, max_size: int = MAX_AUDIO_SIZE) -> str ``` Download audio from URL and return local path. **Parameters** | Name | Type | Required | Default | Description | | --- | --- | --- | --- | --- | | `url` | `str` | `yes` | `none` | Required positional or keyword input. | | `timeout` | `int` | `no` | `120` | Optional positional or keyword input; defaults to `120`. | | `max_size` | `int` | `no` | `MAX_AUDIO_SIZE` | Optional positional or keyword input; defaults to `MAX_AUDIO_SIZE`. | **Returns** - Type: `str` - Direct return expressions: `_download_media(url, 'audio', _AUDIO_EXT_MAP, '.wav', timeout, max_size)` **Exceptions and behavior** Function `download_audio` calls `_download_media`; returns `_download_media(url, 'audio', _AUDIO_EXT_MAP, '.wav', timeout, max_size)`. No direct `raise` statement appears in this definition. [View source #L756-L758](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L756-L758).
vllm_mlx.models.mllm.decode_base64_video · function ```python vllm_mlx.models.mllm.decode_base64_video(base64_string: str, max_length: int = MAX_BASE64_VIDEO_LENGTH) -> str ``` Decode base64 video to temp file and return path. **Parameters** | Name | Type | Required | Default | Description | | --- | --- | --- | --- | --- | | `base64_string` | `str` | `yes` | `none` | Base64-encoded video with data URL prefix | | `max_length` | `int` | `no` | `MAX_BASE64_VIDEO_LENGTH` | Maximum allowed length of base64 string | **Returns** - Type: `str` - Direct return expressions: `_temp_manager.register(temp_file.name)` **Exceptions and behavior** Function `decode_base64_video` calls `len`, `FileSizeExceededError`, `base64_string.startswith`, `base64_string.split`; can raise `FileSizeExceededError`; returns `_temp_manager.register(temp_file.name)`. Directly raised exceptions: `FileSizeExceededError`. [View source #L761-L807](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L761-L807).
vllm_mlx.models.mllm.decode_base64_audio · function ```python vllm_mlx.models.mllm.decode_base64_audio(base64_string: str, max_length: int = MAX_BASE64_AUDIO_LENGTH) -> str ``` Decode base64 audio to temp file and return path. **Parameters** | Name | Type | Required | Default | Description | | --- | --- | --- | --- | --- | | `base64_string` | `str` | `yes` | `none` | Required positional or keyword input. | | `max_length` | `int` | `no` | `MAX_BASE64_AUDIO_LENGTH` | Optional positional or keyword input; defaults to `MAX_BASE64_AUDIO_LENGTH`. | **Returns** - Type: `str` - Direct return expressions: `_temp_manager.register(temp_file.name)` **Exceptions and behavior** Function `decode_base64_audio` calls `len`, `FileSizeExceededError`, `base64_string.startswith`, `base64_string.split`; can raise `FileSizeExceededError`; returns `_temp_manager.register(temp_file.name)`. Directly raised exceptions: `FileSizeExceededError`. [View source #L810-L836](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L810-L836).
vllm_mlx.models.mllm.process_video_input · function ```python vllm_mlx.models.mllm.process_video_input(video: str | dict) -> str ``` Process video input in various formats and return local path. **Parameters** | Name | Type | Required | Default | Description | | --- | --- | --- | --- | --- | | `video` | `str \| dict` | `yes` | `none` | Video input in any supported format | **Returns** - Type: `str` - Direct return expressions: `download_video(video)`; `decode_base64_video(video)` **Exceptions and behavior** Function `process_video_input` calls `isinstance`, `video.get`, `url.get`, `ValueError`; can raise `ValueError`; has 2 explicit return paths. Directly raised exceptions: `ValueError`. [View source #L839-L874](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L839-L874).
vllm_mlx.models.mllm.process_audio_input · function ```python vllm_mlx.models.mllm.process_audio_input(audio: str | dict) -> str ``` Process audio input in various formats and return local path. **Parameters** | Name | Type | Required | Default | Description | | --- | --- | --- | --- | --- | | `audio` | `str \| dict` | `yes` | `none` | Required positional or keyword input. | **Returns** - Type: `str` - Direct return expressions: `decode_base64_audio(audio)`; `download_audio(audio)`; `audio` **Exceptions and behavior** Function `process_audio_input` calls `isinstance`, `audio.get`, `url.get`, `ValueError`; can raise `ValueError`; has 3 explicit return paths. Directly raised exceptions: `ValueError`. [View source #L877-L905](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L877-L905).
vllm_mlx.models.mllm._video_has_audio_track · function ```python vllm_mlx.models.mllm._video_has_audio_track(video_path: str) -> bool ``` Return True if ffprobe finds an audio stream in the video. **Parameters** | Name | Type | Required | Default | Description | | --- | --- | --- | --- | --- | | `video_path` | `str` | `yes` | `none` | Required positional or keyword input. | **Returns** - Type: `bool` - Direct return expressions: `True`; `bool(r.stdout.strip())` **Exceptions and behavior** Function `_video_has_audio_track` calls `shutil.which`, `subprocess.run`, `bool`, `r.stdout.strip`; has 2 explicit return paths. No direct `raise` statement appears in this definition. [View source #L908-L935](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L908-L935).
vllm_mlx.models.mllm._model_has_sound_encoder · function ```python vllm_mlx.models.mllm._model_has_sound_encoder(model) -> bool ``` Whether a loaded model exposes a usable sound encoder. **Parameters** | Name | Type | Required | Default | Description | | --- | --- | --- | --- | --- | | `model` | `not annotated` | `yes` | `none` | Required positional or keyword input. | **Returns** - Type: `bool` - Direct return expressions: `getattr(model, 'sound_encoder', None) is not None` **Exceptions and behavior** Function `_model_has_sound_encoder` calls `getattr`; returns `getattr(model, 'sound_encoder', None) is not None`. No direct `raise` statement appears in this definition. [View source #L938-L947](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L938-L947).
vllm_mlx.models.mllm.extract_audio_from_video · function ```python vllm_mlx.models.mllm.extract_audio_from_video(video_path: str) -> str | None ``` Extract the audio track from a video file as 16 kHz mono WAV. **Parameters** | Name | Type | Required | Default | Description | | --- | --- | --- | --- | --- | | `video_path` | `str` | `yes` | `none` | Required positional or keyword input. | **Returns** - Type: `str | None` - Direct return expressions: `None`; `_temp_manager.register(out_path)` **Exceptions and behavior** Function `extract_audio_from_video` calls `shutil.which`, `logger.warning`, `_video_has_audio_track`, `tempfile.mkstemp`; has 2 explicit return paths. No direct `raise` statement appears in this definition. [View source #L950-L1005](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L950-L1005).
vllm_mlx.models.mllm.save_base64_image · function ```python vllm_mlx.models.mllm.save_base64_image(base64_string: str) -> str ``` Save base64 image to temp file and return path. **Parameters** | Name | Type | Required | Default | Description | | --- | --- | --- | --- | --- | | `base64_string` | `str` | `yes` | `none` | Required positional or keyword input. | **Returns** - Type: `str` - Direct return expressions: `cached_path`; `path` **Exceptions and behavior** Function `save_base64_image` calls `hashlib.sha256(base64_string.encode()).hexdigest`, `hashlib.sha256`, `base64_string.encode`, `Path(cached_path).exists`; has 2 explicit return paths. No direct `raise` statement appears in this definition. [View source #L1012-L1048](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L1012-L1048).
vllm_mlx.models.mllm.process_image_input · function ```python vllm_mlx.models.mllm.process_image_input(image: str | dict) -> str ``` Process image input in various formats and return local path. **Parameters** | Name | Type | Required | Default | Description | | --- | --- | --- | --- | --- | | `image` | `str \| dict` | `yes` | `none` | Required positional or keyword input. | **Returns** - Type: `str` - Direct return expressions: `save_base64_image(image)`; `download_image(image)` **Exceptions and behavior** Function `process_image_input` calls `isinstance`, `image.get`, `url.get`, `ValueError`; can raise `ValueError`; has 2 explicit return paths. Directly raised exceptions: `ValueError`. [View source #L1051-L1080](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L1051-L1080).
vllm_mlx.models.mllm.round_by_factor · function ```python vllm_mlx.models.mllm.round_by_factor(x: int, factor: int) -> int ``` Round to nearest multiple of factor. **Parameters** | Name | Type | Required | Default | Description | | --- | --- | --- | --- | --- | | `x` | `int` | `yes` | `none` | Required positional or keyword input. | | `factor` | `int` | `yes` | `none` | Required positional or keyword input. | **Returns** - Type: `int` - Direct return expressions: `round(x / factor) * factor` **Exceptions and behavior** Function `round_by_factor` calls `round`; returns `round(x / factor) * factor`. No direct `raise` statement appears in this definition. [View source #L1083-L1085](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L1083-L1085).
vllm_mlx.models.mllm.ceil_by_factor · function ```python vllm_mlx.models.mllm.ceil_by_factor(x: float, factor: int) -> int ``` Ceiling to next multiple of factor. **Parameters** | Name | Type | Required | Default | Description | | --- | --- | --- | --- | --- | | `x` | `float` | `yes` | `none` | Required positional or keyword input. | | `factor` | `int` | `yes` | `none` | Required positional or keyword input. | **Returns** - Type: `int` - Direct return expressions: `math.ceil(x / factor) * factor` **Exceptions and behavior** Function `ceil_by_factor` calls `math.ceil`; returns `math.ceil(x / factor) * factor`. No direct `raise` statement appears in this definition. [View source #L1088-L1090](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L1088-L1090).
vllm_mlx.models.mllm.floor_by_factor · function ```python vllm_mlx.models.mllm.floor_by_factor(x: float, factor: int) -> int ``` Floor to previous multiple of factor. **Parameters** | Name | Type | Required | Default | Description | | --- | --- | --- | --- | --- | | `x` | `float` | `yes` | `none` | Required positional or keyword input. | | `factor` | `int` | `yes` | `none` | Required positional or keyword input. | **Returns** - Type: `int` - Direct return expressions: `math.floor(x / factor) * factor` **Exceptions and behavior** Function `floor_by_factor` calls `math.floor`; returns `math.floor(x / factor) * factor`. No direct `raise` statement appears in this definition. [View source #L1093-L1095](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L1093-L1095).
vllm_mlx.models.mllm.smart_nframes · function ```python vllm_mlx.models.mllm.smart_nframes(total_frames: int, video_fps: float, target_fps: float = DEFAULT_FPS, min_frames: int = MIN_FRAMES, max_frames: int = MAX_FRAMES) -> int ``` Calculate optimal number of frames to extract from video. **Parameters** | Name | Type | Required | Default | Description | | --- | --- | --- | --- | --- | | `total_frames` | `int` | `yes` | `none` | Required positional or keyword input. | | `video_fps` | `float` | `yes` | `none` | Required positional or keyword input. | | `target_fps` | `float` | `no` | `DEFAULT_FPS` | Optional positional or keyword input; defaults to `DEFAULT_FPS`. | | `min_frames` | `int` | `no` | `MIN_FRAMES` | Optional positional or keyword input; defaults to `MIN_FRAMES`. | | `max_frames` | `int` | `no` | `MAX_FRAMES` | Optional positional or keyword input; defaults to `MAX_FRAMES`. | **Returns** - Type: `int` - Direct return expressions: `int(nframes)` **Exceptions and behavior** Function `smart_nframes` calls `max`, `min`, `floor_by_factor`, `int`; returns `int(nframes)`. No direct `raise` statement appears in this definition. [View source #L1098-L1120](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L1098-L1120).
vllm_mlx.models.mllm.extract_video_frames_smart · function ```python vllm_mlx.models.mllm.extract_video_frames_smart(video_path: str, fps: float = DEFAULT_FPS, max_frames: int = MAX_FRAMES, resize: tuple[int, int] | None = None) -> list[np.ndarray] ``` Extract frames from video with smart sampling. **Parameters** | Name | Type | Required | Default | Description | | --- | --- | --- | --- | --- | | `video_path` | `str` | `yes` | `none` | Path to video file | | `fps` | `float` | `no` | `DEFAULT_FPS` | Target frames per second (default: 2.0) | | `max_frames` | `int` | `no` | `MAX_FRAMES` | Maximum frames to extract | | `resize` | `tuple[int, int] \| None` | `no` | `None` | Optional (width, height) to resize frames | **Returns** - Type: `list[np.ndarray]` - Direct return expressions: `frames` **Exceptions and behavior** Function `extract_video_frames_smart` calls `ImportError`, `cv2.VideoCapture`, `cap.isOpened`, `ValueError`; can raise `ImportError`, `ValueError`; returns `frames`. Directly raised exceptions: `ImportError`, `ValueError`. [View source #L1123-L1187](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L1123-L1187).
vllm_mlx.models.mllm.save_frames_to_temp · function ```python vllm_mlx.models.mllm.save_frames_to_temp(frames: list[np.ndarray]) -> list[str] ``` Save frame arrays to temporary files and return paths. **Parameters** | Name | Type | Required | Default | Description | | --- | --- | --- | --- | --- | | `frames` | `list[np.ndarray]` | `yes` | `none` | Required positional or keyword input. | **Returns** - Type: `list[str]` - Direct return expressions: `paths` **Exceptions and behavior** Function `save_frames_to_temp` calls `ImportError`, `enumerate`, `Image.fromarray`, `tempfile.NamedTemporaryFile`; can raise `ImportError`; returns `paths`. Directly raised exceptions: `ImportError`. [View source #L1190-L1204](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L1190-L1204).
vllm_mlx.models.mllm.MLXMultimodalLM · class ```python vllm_mlx.models.mllm.MLXMultimodalLM(model_name: str, trust_remote_code: bool = False, enable_cache: bool = True, cache_size: int = 50, max_kv_size: int = 0, draft_model: str | None = None, draft_kind: str | None = None, draft_block_size: int | None = None) ``` Wrapper around mlx-vlm for multimodal inference. **Parameters** | Name | Type | Required | Default | Description | | --- | --- | --- | --- | --- | | `model_name` | `str` | `yes` | `none` | HuggingFace model name or local path | | `trust_remote_code` | `bool` | `no` | `False` | Whether to trust remote code | | `enable_cache` | `bool` | `no` | `True` | Enable KV cache for repeated image/video+prompt (default: True) | | `cache_size` | `int` | `no` | `50` | Maximum cache entries (default: 50) | | `max_kv_size` | `int` | `no` | `0` | Maximum KV cache size per sequence (0 = unbounded) | | `draft_model` | `str \| None` | `no` | `None` | Optional MLLM speculative draft/assistant model path. | | `draft_kind` | `str \| None` | `no` | `None` | Optional mlx-vlm draft kind, for example "mtp". | | `draft_block_size` | `int \| None` | `no` | `None` | Optional speculative block size passed to mlx-vlm. | **Returns** - Constructs: `vllm_mlx.models.mllm.MLXMultimodalLM` **Exceptions and behavior** Class `MLXMultimodalLM` declares 29 direct member(s). No direct `raise` statement appears in this definition. [View source #L1207-L2938](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L1207-L2938).
vllm_mlx.models.mllm.MLXMultimodalLM.__init__ · method ```python vllm_mlx.models.mllm.MLXMultimodalLM.__init__(model_name: str, trust_remote_code: bool = False, enable_cache: bool = True, cache_size: int = 50, max_kv_size: int = 0, draft_model: str | None = None, draft_kind: str | None = None, draft_block_size: int | None = None) -> not annotated ``` Initialize the MLX multimodal language model. **Parameters** | Name | Type | Required | Default | Description | | --- | --- | --- | --- | --- | | `model_name` | `str` | `yes` | `none` | HuggingFace model name or local path | | `trust_remote_code` | `bool` | `no` | `False` | Whether to trust remote code | | `enable_cache` | `bool` | `no` | `True` | Enable KV cache for repeated image/video+prompt (default: True) | | `cache_size` | `int` | `no` | `50` | Maximum cache entries (default: 50) | | `max_kv_size` | `int` | `no` | `0` | Maximum KV cache size per sequence (0 = unbounded) | | `draft_model` | `str \| None` | `no` | `None` | Optional MLLM speculative draft/assistant model path. | | `draft_kind` | `str \| None` | `no` | `None` | Optional mlx-vlm draft kind, for example "mtp". | | `draft_block_size` | `int \| None` | `no` | `None` | Optional speculative block size passed to mlx-vlm. | **Returns** - Type: `not annotated` **Exceptions and behavior** Method `MLXMultimodalLM.__init__` updates `self.model_name`, `self.trust_remote_code`, `self.enable_cache`, `self.max_kv_size`; calls `MLLMPrefixCacheManager`. No direct `raise` statement appears in this definition. [View source #L1235-L1278](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L1235-L1278).
vllm_mlx.models.mllm.MLXMultimodalLM.load · method ```python vllm_mlx.models.mllm.MLXMultimodalLM.load() -> None ``` Load the model and processor. **Parameters** This callable has no explicit inputs. **Returns** - Type: `None` - Direct return expressions: `None` **Exceptions and behavior** Method `MLXMultimodalLM.load` updates `self.model`, `self.processor`, `self.config`, `self._draft_model`; calls `logger.info`, `load`, `load_config`, `self._load_draft_model`; can raise `ImportError`; returns `None`. Directly raised exceptions: `ImportError`. [View source #L1280-L1323](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L1280-L1323).
vllm_mlx.models.mllm.MLXMultimodalLM._load_draft_model · method ```python vllm_mlx.models.mllm.MLXMultimodalLM._load_draft_model() -> not annotated ``` Method `MLXMultimodalLM._load_draft_model` calls `load_gemma4_assistant_drafter`, `load`; has 2 explicit return paths. **Parameters** This callable has no explicit inputs. **Returns** - Type: `not annotated` - Direct return expressions: `load_gemma4_assistant_drafter(self.draft_model_path)`; `draft_model` **Exceptions and behavior** Method `MLXMultimodalLM._load_draft_model` calls `load_gemma4_assistant_drafter`, `load`; has 2 explicit return paths. No direct `raise` statement appears in this definition. [View source #L1325-L1332](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L1325-L1332).
vllm_mlx.models.mllm.MLXMultimodalLM._draft_generation_kwargs · method ```python vllm_mlx.models.mllm.MLXMultimodalLM._draft_generation_kwargs(call_kwargs: dict | None = None) -> dict ``` Return mlx-vlm drafter kwargs when the request explicitly opts in. **Parameters** | Name | Type | Required | Default | Description | | --- | --- | --- | --- | --- | | `call_kwargs` | `dict \| None` | `no` | `None` | Optional positional or keyword input; defaults to `None`. | **Returns** - Type: `dict` - Direct return expressions: `{}`; `kwargs` **Exceptions and behavior** Method `MLXMultimodalLM._draft_generation_kwargs` calls `bool`, `call_kwargs.pop`, `_install_draft_metrics_hooks`; has 2 explicit return paths. No direct `raise` statement appears in this definition. [View source #L1334-L1355](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L1334-L1355).
vllm_mlx.models.mllm.MLXMultimodalLM._reset_draft_metrics · method ```python vllm_mlx.models.mllm.MLXMultimodalLM._reset_draft_metrics() -> int ``` Method `MLXMultimodalLM._reset_draft_metrics` updates `self._draft_model.accept_lens`, `self._draft_model._vllm_mlx_draft_counts`; calls `hasattr`; returns `0`. **Parameters** This callable has no explicit inputs. **Returns** - Type: `int` - Direct return expressions: `0` **Exceptions and behavior** Method `MLXMultimodalLM._reset_draft_metrics` updates `self._draft_model.accept_lens`, `self._draft_model._vllm_mlx_draft_counts`; calls `hasattr`; returns `0`. No direct `raise` statement appears in this definition. [View source #L1357-L1364](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L1357-L1364).
vllm_mlx.models.mllm.MLXMultimodalLM._draft_metrics_since · method ```python vllm_mlx.models.mllm.MLXMultimodalLM._draft_metrics_since(start_accept_lens: int) -> dict[str, int] ``` Method `MLXMultimodalLM._draft_metrics_since` calls `list`, `getattr`, `len`, `int`; has 2 explicit return paths. **Parameters** | Name | Type | Required | Default | Description | | --- | --- | --- | --- | --- | | `start_accept_lens` | `int` | `yes` | `none` | Required positional or keyword input. | **Returns** - Type: `dict[str, int]` - Direct return expressions: `{'mtp_drafts': 0, 'mtp_accepted': 0}`; `{'mtp_drafts': mtp_drafts, 'mtp_accepted': sum((int(value) for value in new_accept_lens))}` **Exceptions and behavior** Method `MLXMultimodalLM._draft_metrics_since` calls `list`, `getattr`, `len`, `int`; has 2 explicit return paths. No direct `raise` statement appears in this definition. [View source #L1366-L1395](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L1366-L1395).
vllm_mlx.models.mllm.MLXMultimodalLM.get_language_model · method ```python vllm_mlx.models.mllm.MLXMultimodalLM.get_language_model() -> not annotated ``` Extract the underlying language model for mlx_lm TextModel construction. **Parameters** This callable has no explicit inputs. **Returns** - Type: `not annotated` - Direct return expressions: `self.model.language_model` **Exceptions and behavior** Method `MLXMultimodalLM.get_language_model` returns `self.model.language_model`. No direct `raise` statement appears in this definition. [View source #L1397-L1399](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L1397-L1399).
vllm_mlx.models.mllm.MLXMultimodalLM.get_tokenizer · method ```python vllm_mlx.models.mllm.MLXMultimodalLM.get_tokenizer() -> not annotated ``` Get the text tokenizer (not the multimodal processor). **Parameters** This callable has no explicit inputs. **Returns** - Type: `not annotated` - Direct return expressions: `self.processor.tokenizer` **Exceptions and behavior** Method `MLXMultimodalLM.get_tokenizer` returns `self.processor.tokenizer`. No direct `raise` statement appears in this definition. [View source #L1401-L1403](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L1401-L1403).
vllm_mlx.models.mllm.MLXMultimodalLM._prepare_images · method ```python vllm_mlx.models.mllm.MLXMultimodalLM._prepare_images(images: list) -> list[str] ``` Process remote/base64 image inputs into local temp file paths. **Parameters** | Name | Type | Required | Default | Description | | --- | --- | --- | --- | --- | | `images` | `list` | `yes` | `none` | Required positional or keyword input. | **Returns** - Type: `list[str]` - Direct return expressions: `processed` **Exceptions and behavior** Method `MLXMultimodalLM._prepare_images` calls `process_image_input`, `processed.append`, `logger.warning`; returns `processed`. No direct `raise` statement appears in this definition. [View source #L1405-L1414](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L1405-L1414).
vllm_mlx.models.mllm.MLXMultimodalLM._prepare_audio · method ```python vllm_mlx.models.mllm.MLXMultimodalLM._prepare_audio(audio_inputs: list) -> list[str] ``` Process audio inputs and return local file paths. **Parameters** | Name | Type | Required | Default | Description | | --- | --- | --- | --- | --- | | `audio_inputs` | `list` | `yes` | `none` | Required positional or keyword input. | **Returns** - Type: `list[str]` - Direct return expressions: `processed` **Exceptions and behavior** Method `MLXMultimodalLM._prepare_audio` calls `process_audio_input`, `processed.append`, `logger.warning`; returns `processed`. No direct `raise` statement appears in this definition. [View source #L1416-L1425](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L1416-L1425).
vllm_mlx.models.mllm.MLXMultimodalLM._prepare_video · method ```python vllm_mlx.models.mllm.MLXMultimodalLM._prepare_video(video_input: str | dict, fps: float = DEFAULT_FPS, max_frames: int = MAX_FRAMES, resolved_path: str | None = None) -> list[str] ``` Process video input and extract frames. **Parameters** | Name | Type | Required | Default | Description | | --- | --- | --- | --- | --- | | `video_input` | `str \| dict` | `yes` | `none` | Video in any supported format | | `fps` | `float` | `no` | `DEFAULT_FPS` | Frames per second to extract | | `max_frames` | `int` | `no` | `MAX_FRAMES` | Maximum frames to extract | | `resolved_path` | `str \| None` | `no` | `None` | Optional pre-resolved local path. Callers that already ran process_video_input (e.g. for parallel audio extraction) pass it here to avoid re-downloading / re-decoding. | **Returns** - Type: `list[str]` - Direct return expressions: `save_frames_to_temp(frames)` **Exceptions and behavior** Method `MLXMultimodalLM._prepare_video` calls `process_video_input`, `extract_video_frames_smart`, `save_frames_to_temp`; returns `save_frames_to_temp(frames)`. No direct `raise` statement appears in this definition. [View source #L1427-L1463](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L1427-L1463).
vllm_mlx.models.mllm.MLXMultimodalLM._collect_video_inputs · method ```python vllm_mlx.models.mllm.MLXMultimodalLM._collect_video_inputs(messages: list[dict]) -> dict[int, list] ``` Collect video inputs from messages, keyed by message index. **Parameters** | Name | Type | Required | Default | Description | | --- | --- | --- | --- | --- | | `messages` | `list[dict]` | `yes` | `none` | Required positional or keyword input. | **Returns** - Type: `dict[int, list]` - Direct return expressions: `video_inputs` **Exceptions and behavior** Method `MLXMultimodalLM._collect_video_inputs` calls `enumerate`, `msg.get`, `isinstance`, `hasattr`; returns `video_inputs`. No direct `raise` statement appears in this definition. [View source #L1465-L1497](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L1465-L1497).
vllm_mlx.models.mllm.MLXMultimodalLM._collect_audio_inputs · method ```python vllm_mlx.models.mllm.MLXMultimodalLM._collect_audio_inputs(messages: list[dict]) -> dict[int, list] ``` Collect audio inputs from messages, keyed by message index. **Parameters** | Name | Type | Required | Default | Description | | --- | --- | --- | --- | --- | | `messages` | `list[dict]` | `yes` | `none` | Required positional or keyword input. | **Returns** - Type: `dict[int, list]` - Direct return expressions: `audio_inputs` **Exceptions and behavior** Method `MLXMultimodalLM._collect_audio_inputs` calls `enumerate`, `msg.get`, `isinstance`, `hasattr`; returns `audio_inputs`. No direct `raise` statement appears in this definition. [View source #L1499-L1528](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L1499-L1528).
vllm_mlx.models.mllm.MLXMultimodalLM._prepare_native_video_inputs · method ```python vllm_mlx.models.mllm.MLXMultimodalLM._prepare_native_video_inputs(messages: list[dict], video_fps: float = DEFAULT_FPS, video_max_frames: int = MAX_FRAMES, tools: list | None = None) -> tuple[str, dict] ``` Preprocess messages into prompt + generation kwargs for native video. **Parameters** | Name | Type | Required | Default | Description | | --- | --- | --- | --- | --- | | `messages` | `list[dict]` | `yes` | `none` | Required positional or keyword input. | | `video_fps` | `float` | `no` | `DEFAULT_FPS` | Optional positional or keyword input; defaults to `DEFAULT_FPS`. | | `video_max_frames` | `int` | `no` | `MAX_FRAMES` | Optional positional or keyword input; defaults to `MAX_FRAMES`. | | `tools` | `list \| None` | `no` | `None` | Optional positional or keyword input; defaults to `None`. | **Returns** - Type: `tuple[str, dict]` - Direct return expressions: `(text, gen_kwargs)` **Exceptions and behavior** Method `MLXMultimodalLM._prepare_native_video_inputs` calls `ImportError`, `self._translate_messages_for_native_video`, `self.processor.apply_chat_template`, `process_vision_info`; can raise `ImportError`; returns `(text, gen_kwargs)`. Directly raised exceptions: `ImportError`. [View source #L1530-L1648](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L1530-L1648).
vllm_mlx.models.mllm.MLXMultimodalLM._generate_native_video · method ```python vllm_mlx.models.mllm.MLXMultimodalLM._generate_native_video(messages: list[dict], max_tokens: int = 256, temperature: float = 0.7, video_fps: float = DEFAULT_FPS, video_max_frames: int = MAX_FRAMES, tools: list | None = None, **kwargs) -> MLLMOutput ``` Generate using native video pipeline (Qwen-family models). **Parameters** | Name | Type | Required | Default | Description | | --- | --- | --- | --- | --- | | `messages` | `list[dict]` | `yes` | `none` | Required positional or keyword input. | | `max_tokens` | `int` | `no` | `256` | Optional positional or keyword input; defaults to `256`. | | `temperature` | `float` | `no` | `0.7` | Optional positional or keyword input; defaults to `0.7`. | | `video_fps` | `float` | `no` | `DEFAULT_FPS` | Optional positional or keyword input; defaults to `DEFAULT_FPS`. | | `video_max_frames` | `int` | `no` | `MAX_FRAMES` | Optional positional or keyword input; defaults to `MAX_FRAMES`. | | `tools` | `list \| None` | `no` | `None` | Optional positional or keyword input; defaults to `None`. | | `**kwargs` | `not annotated` | `no` | `none` | Additional variadic keyword inputs accepted by this callable. | **Returns** - Type: `MLLMOutput` - Direct return expressions: `MLLMOutput(text=result.text, finish_reason='stop', prompt_tokens=getattr(result, 'prompt_tokens', 0), completion_tokens…`; `MLLMOutput(text=str(result), finish_reason='stop')` **Exceptions and behavior** Method `MLXMultimodalLM._generate_native_video` calls `ImportError`, `self._prepare_native_video_inputs`, `generate`, `hasattr`; can raise `ImportError`; has 2 explicit return paths. Directly raised exceptions: `ImportError`. [View source #L1650-L1695](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L1650-L1695).
vllm_mlx.models.mllm.MLXMultimodalLM._translate_messages_for_native_video · method ```python vllm_mlx.models.mllm.MLXMultimodalLM._translate_messages_for_native_video(messages: list[dict], video_fps: float, video_max_frames: int) -> list[dict] ``` Translate OpenAI API format messages to process_vision_info format. **Parameters** | Name | Type | Required | Default | Description | | --- | --- | --- | --- | --- | | `messages` | `list[dict]` | `yes` | `none` | Required positional or keyword input. | | `video_fps` | `float` | `yes` | `none` | Required positional or keyword input. | | `video_max_frames` | `int` | `yes` | `none` | Required positional or keyword input. | **Returns** - Type: `list[dict]` - Direct return expressions: `translated` **Exceptions and behavior** Method `MLXMultimodalLM._translate_messages_for_native_video` calls `msg.get`, `isinstance`, `translated.append`, `str`; returns `translated`. No direct `raise` statement appears in this definition. [View source #L1697-L1832](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L1697-L1832).
vllm_mlx.models.mllm.MLXMultimodalLM.generate · method ```python vllm_mlx.models.mllm.MLXMultimodalLM.generate(prompt: str, images: list | None = None, videos: list | None = None, audio: list[str] | None = None, max_tokens: int = 256, temperature: float = 0.7, top_p: float = 0.9, video_fps: float = DEFAULT_FPS, video_max_frames: int = MAX_FRAMES, use_cache: bool = True, **kwargs) -> MLLMOutput ``` Generate text from multimodal input. **Parameters** | Name | Type | Required | Default | Description | | --- | --- | --- | --- | --- | | `prompt` | `str` | `yes` | `none` | Text prompt/question | | `images` | `list \| None` | `no` | `None` | List of image URLs or base64 strings | | `videos` | `list \| None` | `no` | `None` | List of video inputs (URLs, base64, or OpenAI format dicts) | | `audio` | `list[str] \| None` | `no` | `None` | List of audio file paths | | `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 | | `video_fps` | `float` | `no` | `DEFAULT_FPS` | FPS for video frame extraction (default: 2.0) | | `video_max_frames` | `int` | `no` | `MAX_FRAMES` | Max frames to extract from video | | `use_cache` | `bool` | `no` | `True` | Whether to use KV cache (default: True) | | `**kwargs` | `not annotated` | `no` | `none` | Additional generation parameters | **Returns** - Type: `MLLMOutput` - Direct return expressions: `MLLMOutput(text=output_text, finish_reason='stop', prompt_tokens=prompt_tokens, completion_tokens=generation_tokens, **…` **Exceptions and behavior** Method `MLXMultimodalLM.generate` calls `self.load`, `all_images.extend`, `self._prepare_images`, `all_sources.extend`; returns `MLLMOutput(text=output_text, finish_reason='stop', prompt_tokens=prompt_tokens, completion_tokens=generation_tokens, **…`. No direct `raise` statement appears in this definition. [View source #L1834-L2002](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L1834-L2002).
vllm_mlx.models.mllm.MLXMultimodalLM.stream_generate · method ```python vllm_mlx.models.mllm.MLXMultimodalLM.stream_generate(prompt: str, images: list | None = None, videos: list[str] | None = None, audio: list[str] | None = None, max_tokens: int = 256, temperature: float = 0.7, video_fps: float = DEFAULT_FPS, **kwargs) -> Iterator[str] ``` Stream text generation for multimodal input. **Parameters** | Name | Type | Required | Default | Description | | --- | --- | --- | --- | --- | | `prompt` | `str` | `yes` | `none` | Text prompt | | `images` | `list \| None` | `no` | `None` | List of image inputs | | `videos` | `list[str] \| None` | `no` | `None` | List of video paths | | `audio` | `list[str] \| None` | `no` | `None` | List of audio inputs | | `max_tokens` | `int` | `no` | `256` | Maximum tokens to generate | | `temperature` | `float` | `no` | `0.7` | Sampling temperature | | `video_fps` | `float` | `no` | `DEFAULT_FPS` | FPS for video frame extraction | | `**kwargs` | `not annotated` | `no` | `none` | Additional parameters | **Returns** - Type: `Iterator[str]` - Direct return expressions: `None` - Yields values incrementally. **Exceptions and behavior** Method `MLXMultimodalLM.stream_generate` calls `self.load`, `self.generate`, `all_images.extend`, `self._prepare_images`; yields values incrementally; returns `None`. No direct `raise` statement appears in this definition. [View source #L2004-L2093](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L2004-L2093).
vllm_mlx.models.mllm.MLXMultimodalLM.chat · method ```python vllm_mlx.models.mllm.MLXMultimodalLM.chat(messages: list[dict], max_tokens: int = 256, temperature: float = 0.7, **kwargs) -> MLLMOutput ``` Chat with OpenAI-compatible message format. **Parameters** | Name | Type | Required | Default | Description | | --- | --- | --- | --- | --- | | `messages` | `list[dict]` | `yes` | `none` | List of chat messages (OpenAI format) | | `max_tokens` | `int` | `no` | `256` | Maximum tokens to generate | | `temperature` | `float` | `no` | `0.7` | Sampling temperature | | `**kwargs` | `not annotated` | `no` | `none` | Additional parameters | **Returns** - Type: `MLLMOutput` - Direct return expressions: `self._generate_native_video(messages=messages, max_tokens=max_tokens, temperature=temperature, video_fps=video_fps, vid…`; `MLLMOutput(text=output_text, finish_reason='stop', prompt_tokens=prompt_tokens, completion_tokens=generation_tokens, **…` **Exceptions and behavior** Method `MLXMultimodalLM.chat` calls `self.load`, `logger.info`, `len`, `kwargs.pop`; has 2 explicit return paths. No direct `raise` statement appears in this definition. [View source #L2095-L2487](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L2095-L2487).
vllm_mlx.models.mllm.MLXMultimodalLM.stream_chat · method ```python vllm_mlx.models.mllm.MLXMultimodalLM.stream_chat(messages: list[dict], max_tokens: int = 256, temperature: float = 0.7, **kwargs) -> Iterator[MLLMOutput] ``` Stream chat with OpenAI-compatible message format. **Parameters** | Name | Type | Required | Default | Description | | --- | --- | --- | --- | --- | | `messages` | `list[dict]` | `yes` | `none` | List of chat messages (OpenAI format) | | `max_tokens` | `int` | `no` | `256` | Maximum tokens to generate | | `temperature` | `float` | `no` | `0.7` | Sampling temperature | | `**kwargs` | `not annotated` | `no` | `none` | Additional parameters | **Returns** - Type: `Iterator[MLLMOutput]` - Direct return expressions: `None` - Yields values incrementally. **Exceptions and behavior** Method `MLXMultimodalLM.stream_chat` calls `self.load`, `self.chat`, `kwargs.pop`, `chat_template_kwargs.pop`; yields values incrementally; returns `None`. No direct `raise` statement appears in this definition. [View source #L2489-L2737](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L2489-L2737).
vllm_mlx.models.mllm.MLXMultimodalLM.describe_image · method ```python vllm_mlx.models.mllm.MLXMultimodalLM.describe_image(image: str, prompt: str = 'Describe this image in detail.', max_tokens: int = 512, **kwargs) -> str ``` Convenience method to describe an image. **Parameters** | Name | Type | Required | Default | Description | | --- | --- | --- | --- | --- | | `image` | `str` | `yes` | `none` | Image path, URL, or base64 string | | `prompt` | `str` | `no` | `'Describe this image in detail.'` | Description prompt | | `max_tokens` | `int` | `no` | `512` | Maximum tokens | | `**kwargs` | `not annotated` | `no` | `none` | Additional parameters | **Returns** - Type: `str` - Direct return expressions: `output.text` **Exceptions and behavior** Method `MLXMultimodalLM.describe_image` calls `self.generate`; returns `output.text`. No direct `raise` statement appears in this definition. [View source #L2739-L2764](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L2739-L2764).
vllm_mlx.models.mllm.MLXMultimodalLM.answer_about_image · method ```python vllm_mlx.models.mllm.MLXMultimodalLM.answer_about_image(image: str, question: str, max_tokens: int = 256, **kwargs) -> str ``` Answer a question about an image. **Parameters** | Name | Type | Required | Default | Description | | --- | --- | --- | --- | --- | | `image` | `str` | `yes` | `none` | Image path, URL, or base64 string | | `question` | `str` | `yes` | `none` | Question about the image | | `max_tokens` | `int` | `no` | `256` | Maximum tokens | | `**kwargs` | `not annotated` | `no` | `none` | Additional parameters | **Returns** - Type: `str` - Direct return expressions: `output.text` **Exceptions and behavior** Method `MLXMultimodalLM.answer_about_image` calls `self.generate`; returns `output.text`. No direct `raise` statement appears in this definition. [View source #L2766-L2791](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L2766-L2791).
vllm_mlx.models.mllm.MLXMultimodalLM.describe_video · method ```python vllm_mlx.models.mllm.MLXMultimodalLM.describe_video(video: str | dict, prompt: str = 'Describe what happens in this video.', fps: float = 2.0, max_frames: int = 32, max_tokens: int = 512, **kwargs) -> str ``` Describe a video using frame extraction. **Parameters** | Name | Type | Required | Default | Description | | --- | --- | --- | --- | --- | | `video` | `str \| dict` | `yes` | `none` | Video file path, URL, base64, or OpenAI format dict | | `prompt` | `str` | `no` | `'Describe what happens in this video.'` | Description prompt | | `fps` | `float` | `no` | `2.0` | Frames per second to extract | | `max_frames` | `int` | `no` | `32` | Maximum frames to extract | | `max_tokens` | `int` | `no` | `512` | Maximum tokens to generate | | `**kwargs` | `not annotated` | `no` | `none` | Additional variadic keyword inputs accepted by this callable. | **Returns** - Type: `str` - Direct return expressions: `output.text` **Exceptions and behavior** Method `MLXMultimodalLM.describe_video` calls `self.generate`; returns `output.text`. No direct `raise` statement appears in this definition. [View source #L2793-L2830](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L2793-L2830).
vllm_mlx.models.mllm.MLXMultimodalLM.get_cache_stats · method ```python vllm_mlx.models.mllm.MLXMultimodalLM.get_cache_stats() -> dict ``` Get MLLM cache statistics. **Parameters** This callable has no explicit inputs. **Returns** - Type: `dict` - Direct return expressions: `{'enabled': False}`; `stats` **Exceptions and behavior** Method `MLXMultimodalLM.get_cache_stats` calls `self._cache_manager.get_stats`, `len`; has 2 explicit return paths. No direct `raise` statement appears in this definition. [View source #L2832-L2846](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L2832-L2846).
vllm_mlx.models.mllm.MLXMultimodalLM.clear_cache · method ```python vllm_mlx.models.mllm.MLXMultimodalLM.clear_cache() -> None ``` Clear the MLLM KV cache. **Parameters** This callable has no explicit inputs. **Returns** - Type: `None` **Exceptions and behavior** Method `MLXMultimodalLM.clear_cache` calls `self._cache_manager.clear`, `logger.info`. No direct `raise` statement appears in this definition. [View source #L2848-L2852](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L2848-L2852).
vllm_mlx.models.mllm.MLXMultimodalLM.get_model_info · method ```python vllm_mlx.models.mllm.MLXMultimodalLM.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 `MLXMultimodalLM.get_model_info` calls `getattr`, `self._cache_manager.get_stats`; has 2 explicit return paths. No direct `raise` statement appears in this definition. [View source #L2854-L2874](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L2854-L2874).
vllm_mlx.models.mllm.MLXMultimodalLM.list_supported_model_families · method ```python vllm_mlx.models.mllm.MLXMultimodalLM.list_supported_model_families() -> dict[str, str] ``` List supported model families and their patterns. **Parameters** This callable has no explicit inputs. **Returns** - Type: `dict[str, str]` - Direct return expressions: `{'Qwen-VL': 'Qwen VL models (Qwen2-VL, Qwen2.5-VL, Qwen3-VL, etc.)', 'LLaVA': 'LLaVA vision-language models', 'Idefics'…` **Exceptions and behavior** Method `MLXMultimodalLM.list_supported_model_families` returns `{'Qwen-VL': 'Qwen VL models (Qwen2-VL, Qwen2.5-VL, Qwen3-VL, etc.)', 'LLaVA': 'LLaVA vision-language models', 'Idefics'…`. No direct `raise` statement appears in this definition. [View source #L2877-L2897](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L2877-L2897).
vllm_mlx.models.mllm.MLXMultimodalLM.is_mllm_model · method ```python vllm_mlx.models.mllm.MLXMultimodalLM.is_mllm_model(model_name: str) -> bool ``` Check if a model name indicates an MLLM model. **Parameters** | Name | Type | Required | Default | Description | | --- | --- | --- | --- | --- | | `model_name` | `str` | `yes` | `none` | Required positional or keyword input. | **Returns** - Type: `bool` - Direct return expressions: `any((pattern.lower() in model_lower for pattern in mllm_patterns))` **Exceptions and behavior** Method `MLXMultimodalLM.is_mllm_model` calls `model_name.lower`, `any`, `pattern.lower`; returns `any((pattern.lower() in model_lower for pattern in mllm_patterns))`. No direct `raise` statement appears in this definition. [View source #L2900-L2934](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L2900-L2934).
vllm_mlx.models.mllm.MLXMultimodalLM.__repr__ · method ```python vllm_mlx.models.mllm.MLXMultimodalLM.__repr__() -> str ``` Method `MLXMultimodalLM.__repr__` returns `f''`. **Parameters** This callable has no explicit inputs. **Returns** - Type: `str` - Direct return expressions: `f''` **Exceptions and behavior** Method `MLXMultimodalLM.__repr__` returns `f''`. No direct `raise` statement appears in this definition. [View source #L2936-L2938](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L2936-L2938).
## 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 | | --- | --- | --- | --- | --- | | [`TempFileManager`](#contract-vllm_mlx.models.mllm.TempFileManager) | class | `TempFileManager()` | Thread-safe manager for tracking and cleaning up temporary files. | [#L41-L86](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L41-L86) | | [`TempFileManager.__init__`](#contract-vllm_mlx.models.mllm.TempFileManager.__init__) | method | `TempFileManager.__init__() -> not annotated` | Method `TempFileManager.__init__` updates `self._files`, `self._lock`; calls `set`, `threading.Lock`, `atexit.register`. | [#L44-L47](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L44-L47) | | [`TempFileManager.register`](#contract-vllm_mlx.models.mllm.TempFileManager.register) | method | `TempFileManager.register(path: str) -> str` | Register a temp file for tracking. | [#L49-L53](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L49-L53) | | [`TempFileManager.cleanup`](#contract-vllm_mlx.models.mllm.TempFileManager.cleanup) | method | `TempFileManager.cleanup(path: str) -> bool` | Clean up a specific temp file. | [#L55-L67](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L55-L67) | | [`TempFileManager.cleanup_all`](#contract-vllm_mlx.models.mllm.TempFileManager.cleanup_all) | method | `TempFileManager.cleanup_all() -> int` | Clean up all tracked temp files. | [#L69-L86](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L69-L86) | | [`cleanup_temp_file`](#contract-vllm_mlx.models.mllm.cleanup_temp_file) | function | `cleanup_temp_file(path: str) -> bool` | Clean up a specific temporary file. | [#L93-L95](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L93-L95) | | [`cleanup_all_temp_files`](#contract-vllm_mlx.models.mllm.cleanup_all_temp_files) | function | `cleanup_all_temp_files() -> int` | Clean up all tracked temporary files. | [#L98-L100](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L98-L100) | | [`FileSizeExceededError`](#contract-vllm_mlx.models.mllm.FileSizeExceededError) | class | `FileSizeExceededError()` | Raised when a downloaded file exceeds the size limit. | [#L119-L122](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L119-L122) | | [`UnsafeRemoteURLError`](#contract-vllm_mlx.models.mllm.UnsafeRemoteURLError) | class | `UnsafeRemoteURLError(message: str, *, public_message: str = 'Remote media URL is not allowed')` | Raised when a remote media URL targets an unsafe destination. | [#L125-L135](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L125-L135) | | [`UnsafeRemoteURLError.__init__`](#contract-vllm_mlx.models.mllm.UnsafeRemoteURLError.__init__) | method | `UnsafeRemoteURLError.__init__(message: str, *, public_message: str = 'Remote media URL is not allowed') -> None` | Method `UnsafeRemoteURLError.__init__` updates `self.public_message`; calls `super().__init__`, `super`. | [#L128-L135](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L128-L135) | | [`_normalize_content_part`](#contract-vllm_mlx.models.mllm._normalize_content_part) | function | `_normalize_content_part(item: object) -> object` | Convert Pydantic content parts into plain Python objects. | [#L138-L144](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L138-L144) | | [`_extract_media_url`](#contract-vllm_mlx.models.mllm._extract_media_url) | function | `_extract_media_url(item: dict, item_type: str) -> str` | Function `_extract_media_url` calls `item.get`, `isinstance`, `media_value.get`; has 2 explicit return paths. | [#L147-L161](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L147-L161) | | [`_text_content_part`](#contract-vllm_mlx.models.mllm._text_content_part) | function | `_text_content_part(text: str) -> dict[str, str]` | Function `_text_content_part` returns `{'type': 'text', 'text': text, 'content': text}`. | [#L164-L165](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L164-L165) | | [`_append_text_content_part`](#contract-vllm_mlx.models.mllm._append_text_content_part) | function | `_append_text_content_part(built_parts: list[dict[str, str]], text_parts: list[str], text: str) -> None` | Function `_append_text_content_part` calls `built_parts.append`, `_text_content_part`, `text_parts.append`; returns `None`. | [#L168-L174](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L168-L174) | | [`_build_string_mllm_message_content`](#contract-vllm_mlx.models.mllm._build_string_mllm_message_content) | function | `_build_string_mllm_message_content(content: str, role: str) -> tuple[object, bool]` | Function `_build_string_mllm_message_content` calls `_text_content_part`; has 3 explicit return paths. | [#L177-L182](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L177-L182) | | [`_append_ordered_mllm_content_part`](#contract-vllm_mlx.models.mllm._append_ordered_mllm_content_part) | function | `_append_ordered_mllm_content_part(raw_item: object, *, built_parts: list[dict[str, str]], text_parts: list[str], all_image_urls: list[str], video_frame_count: int) -> int` | Function `_append_ordered_mllm_content_part` calls `_normalize_content_part`, `isinstance`, `_append_text_content_part`, `item.get`; has 2 explicit return paths. | [#L185-L220](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L185-L220) | | [`_build_ordered_mllm_message_content`](#contract-vllm_mlx.models.mllm._build_ordered_mllm_message_content) | function | `_build_ordered_mllm_message_content(content: object, *, role: str, all_image_urls: list[str], video_frame_count: int = 0) -> tuple[object, bool]` | Build template content while preserving OpenAI media/text part order. | [#L223-L254](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L223-L254) | | [`_normalize_mllm_tool_calls`](#contract-vllm_mlx.models.mllm._normalize_mllm_tool_calls) | function | `_normalize_mllm_tool_calls(tool_calls: list) -> list` | Normalize replayed assistant tool calls for chat templates. | [#L257-L268](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L257-L268) | | [`_build_mllm_chat_messages`](#contract-vllm_mlx.models.mllm._build_mllm_chat_messages) | function | `_build_mllm_chat_messages(messages: list[dict], *, all_image_urls: list[str], video_frame_counts: dict[int, int]) -> list[dict]` | Build chat-template messages without reordering multimodal content parts. | [#L271-L315](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L271-L315) | | [`MultimodalInput`](#contract-vllm_mlx.models.mllm.MultimodalInput) | class | `MultimodalInput(prompt: str, images: list[str] = field(default_factory=list), videos: list[str] = field(default_factory=list), audio: list[str] = field(default_factory=list))` | Input for multimodal generation. | [#L319-L325](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L319-L325) | | [`MLLMOutput`](#contract-vllm_mlx.models.mllm.MLLMOutput) | class | `MLLMOutput(text: str, finish_reason: str \| None = None, prompt_tokens: int = 0, completion_tokens: int = 0, mtp_drafts: int = 0, mtp_accepted: int = 0)` | Output from multimodal language model. | [#L329-L337](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L329-L337) | | [`load_gemma4_assistant_drafter`](#contract-vllm_mlx.models.mllm.load_gemma4_assistant_drafter) | function | `load_gemma4_assistant_drafter(model_path: str) -> not annotated` | Load a Gemma 4 assistant drafter for mlx-vlm speculative decoding. | [#L340-L381](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L340-L381) | | [`_count_draft_tokens`](#contract-vllm_mlx.models.mllm._count_draft_tokens) | function | `_count_draft_tokens(draft_tokens) -> int` | Best-effort drafted-token count for an mlx-vlm drafter output. | [#L387-L398](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L387-L398) | | [`_install_draft_metrics_hooks`](#contract-vllm_mlx.models.mllm._install_draft_metrics_hooks) | function | `_install_draft_metrics_hooks(draft_model) -> None` | Record actual drafted token counts from mlx-vlm assistant drafters. | [#L401-L428](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L401-L428) | | [`_install_draft_metrics_hooks.draft_block_with_metrics`](#contract-vllm_mlx.models.mllm._install_draft_metrics_hooks.draft_block_with_metrics) | nested function | `_install_draft_metrics_hooks.draft_block_with_metrics(*args, **kwargs) -> not annotated` | Nested Function `_install_draft_metrics_hooks.draft_block_with_metrics` calls `draft_block`, `draft_model._vllm_mlx_draft_counts.append`, `_count_draft_tokens`; returns `draft_tokens`. | [#L412-L415](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L412-L415) | | [`_install_draft_metrics_hooks.reset_with_metrics`](#contract-vllm_mlx.models.mllm._install_draft_metrics_hooks.reset_with_metrics) | nested function | `_install_draft_metrics_hooks.reset_with_metrics(*args, **kwargs) -> not annotated` | Nested Function `_install_draft_metrics_hooks.reset_with_metrics` calls `reset`; returns `reset(*args, **kwargs)`. | [#L422-L424](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L422-L424) | | [`is_base64_image`](#contract-vllm_mlx.models.mllm.is_base64_image) | function | `is_base64_image(s: str) -> bool` | Check if string is base64-encoded image data. | [#L431-L435](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L431-L435) | | [`is_url`](#contract-vllm_mlx.models.mllm.is_url) | function | `is_url(s: str) -> bool` | Check if string is a URL. | [#L438-L440](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L438-L440) | | [`is_base64_video`](#contract-vllm_mlx.models.mllm.is_base64_video) | function | `is_base64_video(s: str) -> bool` | Check if string is base64-encoded video data. | [#L443-L445](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L443-L445) | | [`is_base64_audio`](#contract-vllm_mlx.models.mllm.is_base64_audio) | function | `is_base64_audio(s: str) -> bool` | Check if string is base64-encoded audio data. | [#L448-L450](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L448-L450) | | [`decode_base64_image`](#contract-vllm_mlx.models.mllm.decode_base64_image) | function | `decode_base64_image(base64_string: str, max_length: int = MAX_BASE64_IMAGE_LENGTH) -> bytes` | Decode base64 image to bytes. | [#L453-L480](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L453-L480) | | [`_validate_url_safety`](#contract-vllm_mlx.models.mllm._validate_url_safety) | function | `_validate_url_safety(url: str) -> None` | Reject remote URLs that target local or private network resources. | [#L483-L519](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L483-L519) | | [`_request_with_safe_redirects`](#contract-vllm_mlx.models.mllm._request_with_safe_redirects) | function | `_request_with_safe_redirects(method: str, url: str, *, timeout: int, headers: dict[str, str], stream: bool = False, max_redirects: int = 5) -> not annotated` | Issue a requests call while validating every redirect target. | [#L522-L557](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L522-L557) | | [`download_image`](#contract-vllm_mlx.models.mllm.download_image) | function | `download_image(url: str, timeout: int = 30, max_size: int = MAX_IMAGE_SIZE) -> str` | Download image from URL and return local path. | [#L560-L645](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L560-L645) | | [`_download_media`](#contract-vllm_mlx.models.mllm._download_media) | function | `_download_media(url: str, media_type: str, ext_map: dict[str, str], default_ext: str, timeout: int, max_size: int) -> str` | Download media from URL, enforce size limits, and return a local temp path. | [#L670-L748](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L670-L748) | | [`download_video`](#contract-vllm_mlx.models.mllm.download_video) | function | `download_video(url: str, timeout: int = 120, max_size: int = MAX_VIDEO_SIZE) -> str` | Download video from URL and return local path. | [#L751-L753](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L751-L753) | | [`download_audio`](#contract-vllm_mlx.models.mllm.download_audio) | function | `download_audio(url: str, timeout: int = 120, max_size: int = MAX_AUDIO_SIZE) -> str` | Download audio from URL and return local path. | [#L756-L758](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L756-L758) | | [`decode_base64_video`](#contract-vllm_mlx.models.mllm.decode_base64_video) | function | `decode_base64_video(base64_string: str, max_length: int = MAX_BASE64_VIDEO_LENGTH) -> str` | Decode base64 video to temp file and return path. | [#L761-L807](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L761-L807) | | [`decode_base64_audio`](#contract-vllm_mlx.models.mllm.decode_base64_audio) | function | `decode_base64_audio(base64_string: str, max_length: int = MAX_BASE64_AUDIO_LENGTH) -> str` | Decode base64 audio to temp file and return path. | [#L810-L836](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L810-L836) | | [`process_video_input`](#contract-vllm_mlx.models.mllm.process_video_input) | function | `process_video_input(video: str \| dict) -> str` | Process video input in various formats and return local path. | [#L839-L874](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L839-L874) | | [`process_audio_input`](#contract-vllm_mlx.models.mllm.process_audio_input) | function | `process_audio_input(audio: str \| dict) -> str` | Process audio input in various formats and return local path. | [#L877-L905](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L877-L905) | | [`_video_has_audio_track`](#contract-vllm_mlx.models.mllm._video_has_audio_track) | function | `_video_has_audio_track(video_path: str) -> bool` | Return True if ffprobe finds an audio stream in the video. | [#L908-L935](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L908-L935) | | [`_model_has_sound_encoder`](#contract-vllm_mlx.models.mllm._model_has_sound_encoder) | function | `_model_has_sound_encoder(model) -> bool` | Whether a loaded model exposes a usable sound encoder. | [#L938-L947](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L938-L947) | | [`extract_audio_from_video`](#contract-vllm_mlx.models.mllm.extract_audio_from_video) | function | `extract_audio_from_video(video_path: str) -> str \| None` | Extract the audio track from a video file as 16 kHz mono WAV. | [#L950-L1005](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L950-L1005) | | [`save_base64_image`](#contract-vllm_mlx.models.mllm.save_base64_image) | function | `save_base64_image(base64_string: str) -> str` | Save base64 image to temp file and return path. | [#L1012-L1048](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L1012-L1048) | | [`process_image_input`](#contract-vllm_mlx.models.mllm.process_image_input) | function | `process_image_input(image: str \| dict) -> str` | Process image input in various formats and return local path. | [#L1051-L1080](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L1051-L1080) | | [`round_by_factor`](#contract-vllm_mlx.models.mllm.round_by_factor) | function | `round_by_factor(x: int, factor: int) -> int` | Round to nearest multiple of factor. | [#L1083-L1085](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L1083-L1085) | | [`ceil_by_factor`](#contract-vllm_mlx.models.mllm.ceil_by_factor) | function | `ceil_by_factor(x: float, factor: int) -> int` | Ceiling to next multiple of factor. | [#L1088-L1090](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L1088-L1090) | | [`floor_by_factor`](#contract-vllm_mlx.models.mllm.floor_by_factor) | function | `floor_by_factor(x: float, factor: int) -> int` | Floor to previous multiple of factor. | [#L1093-L1095](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L1093-L1095) | | [`smart_nframes`](#contract-vllm_mlx.models.mllm.smart_nframes) | function | `smart_nframes(total_frames: int, video_fps: float, target_fps: float = DEFAULT_FPS, min_frames: int = MIN_FRAMES, max_frames: int = MAX_FRAMES) -> int` | Calculate optimal number of frames to extract from video. | [#L1098-L1120](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L1098-L1120) | | [`extract_video_frames_smart`](#contract-vllm_mlx.models.mllm.extract_video_frames_smart) | function | `extract_video_frames_smart(video_path: str, fps: float = DEFAULT_FPS, max_frames: int = MAX_FRAMES, resize: tuple[int, int] \| None = None) -> list[np.ndarray]` | Extract frames from video with smart sampling. | [#L1123-L1187](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L1123-L1187) | | [`save_frames_to_temp`](#contract-vllm_mlx.models.mllm.save_frames_to_temp) | function | `save_frames_to_temp(frames: list[np.ndarray]) -> list[str]` | Save frame arrays to temporary files and return paths. | [#L1190-L1204](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L1190-L1204) | | [`MLXMultimodalLM`](#contract-vllm_mlx.models.mllm.MLXMultimodalLM) | class | `MLXMultimodalLM(model_name: str, trust_remote_code: bool = False, enable_cache: bool = True, cache_size: int = 50, max_kv_size: int = 0, draft_model: str \| None = None, draft_kind: str \| None = None, draft_block_size: int \| None = None)` | Wrapper around mlx-vlm for multimodal inference. | [#L1207-L2938](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L1207-L2938) | | [`MLXMultimodalLM.__init__`](#contract-vllm_mlx.models.mllm.MLXMultimodalLM.__init__) | method | `MLXMultimodalLM.__init__(model_name: str, trust_remote_code: bool = False, enable_cache: bool = True, cache_size: int = 50, max_kv_size: int = 0, draft_model: str \| None = None, draft_kind: str \| None = None, draft_block_size: int \| None = None) -> not annotated` | Initialize the MLX multimodal language model. | [#L1235-L1278](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L1235-L1278) | | [`MLXMultimodalLM.load`](#contract-vllm_mlx.models.mllm.MLXMultimodalLM.load) | method | `MLXMultimodalLM.load() -> None` | Load the model and processor. | [#L1280-L1323](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L1280-L1323) | | [`MLXMultimodalLM._load_draft_model`](#contract-vllm_mlx.models.mllm.MLXMultimodalLM._load_draft_model) | method | `MLXMultimodalLM._load_draft_model() -> not annotated` | Method `MLXMultimodalLM._load_draft_model` calls `load_gemma4_assistant_drafter`, `load`; has 2 explicit return paths. | [#L1325-L1332](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L1325-L1332) | | [`MLXMultimodalLM._draft_generation_kwargs`](#contract-vllm_mlx.models.mllm.MLXMultimodalLM._draft_generation_kwargs) | method | `MLXMultimodalLM._draft_generation_kwargs(call_kwargs: dict \| None = None) -> dict` | Return mlx-vlm drafter kwargs when the request explicitly opts in. | [#L1334-L1355](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L1334-L1355) | | [`MLXMultimodalLM._reset_draft_metrics`](#contract-vllm_mlx.models.mllm.MLXMultimodalLM._reset_draft_metrics) | method | `MLXMultimodalLM._reset_draft_metrics() -> int` | Method `MLXMultimodalLM._reset_draft_metrics` updates `self._draft_model.accept_lens`, `self._draft_model._vllm_mlx_draft_counts`; calls `hasattr`; returns `0`. | [#L1357-L1364](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L1357-L1364) | | [`MLXMultimodalLM._draft_metrics_since`](#contract-vllm_mlx.models.mllm.MLXMultimodalLM._draft_metrics_since) | method | `MLXMultimodalLM._draft_metrics_since(start_accept_lens: int) -> dict[str, int]` | Method `MLXMultimodalLM._draft_metrics_since` calls `list`, `getattr`, `len`, `int`; has 2 explicit return paths. | [#L1366-L1395](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L1366-L1395) | | [`MLXMultimodalLM.get_language_model`](#contract-vllm_mlx.models.mllm.MLXMultimodalLM.get_language_model) | method | `MLXMultimodalLM.get_language_model() -> not annotated` | Extract the underlying language model for mlx_lm TextModel construction. | [#L1397-L1399](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L1397-L1399) | | [`MLXMultimodalLM.get_tokenizer`](#contract-vllm_mlx.models.mllm.MLXMultimodalLM.get_tokenizer) | method | `MLXMultimodalLM.get_tokenizer() -> not annotated` | Get the text tokenizer (not the multimodal processor). | [#L1401-L1403](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L1401-L1403) | | [`MLXMultimodalLM._prepare_images`](#contract-vllm_mlx.models.mllm.MLXMultimodalLM._prepare_images) | method | `MLXMultimodalLM._prepare_images(images: list) -> list[str]` | Process remote/base64 image inputs into local temp file paths. | [#L1405-L1414](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L1405-L1414) | | [`MLXMultimodalLM._prepare_audio`](#contract-vllm_mlx.models.mllm.MLXMultimodalLM._prepare_audio) | method | `MLXMultimodalLM._prepare_audio(audio_inputs: list) -> list[str]` | Process audio inputs and return local file paths. | [#L1416-L1425](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L1416-L1425) | | [`MLXMultimodalLM._prepare_video`](#contract-vllm_mlx.models.mllm.MLXMultimodalLM._prepare_video) | method | `MLXMultimodalLM._prepare_video(video_input: str \| dict, fps: float = DEFAULT_FPS, max_frames: int = MAX_FRAMES, resolved_path: str \| None = None) -> list[str]` | Process video input and extract frames. | [#L1427-L1463](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L1427-L1463) | | [`MLXMultimodalLM._collect_video_inputs`](#contract-vllm_mlx.models.mllm.MLXMultimodalLM._collect_video_inputs) | method | `MLXMultimodalLM._collect_video_inputs(messages: list[dict]) -> dict[int, list]` | Collect video inputs from messages, keyed by message index. | [#L1465-L1497](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L1465-L1497) | | [`MLXMultimodalLM._collect_audio_inputs`](#contract-vllm_mlx.models.mllm.MLXMultimodalLM._collect_audio_inputs) | method | `MLXMultimodalLM._collect_audio_inputs(messages: list[dict]) -> dict[int, list]` | Collect audio inputs from messages, keyed by message index. | [#L1499-L1528](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L1499-L1528) | | [`MLXMultimodalLM._prepare_native_video_inputs`](#contract-vllm_mlx.models.mllm.MLXMultimodalLM._prepare_native_video_inputs) | method | `MLXMultimodalLM._prepare_native_video_inputs(messages: list[dict], video_fps: float = DEFAULT_FPS, video_max_frames: int = MAX_FRAMES, tools: list \| None = None) -> tuple[str, dict]` | Preprocess messages into prompt + generation kwargs for native video. | [#L1530-L1648](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L1530-L1648) | | [`MLXMultimodalLM._generate_native_video`](#contract-vllm_mlx.models.mllm.MLXMultimodalLM._generate_native_video) | method | `MLXMultimodalLM._generate_native_video(messages: list[dict], max_tokens: int = 256, temperature: float = 0.7, video_fps: float = DEFAULT_FPS, video_max_frames: int = MAX_FRAMES, tools: list \| None = None, **kwargs) -> MLLMOutput` | Generate using native video pipeline (Qwen-family models). | [#L1650-L1695](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L1650-L1695) | | [`MLXMultimodalLM._translate_messages_for_native_video`](#contract-vllm_mlx.models.mllm.MLXMultimodalLM._translate_messages_for_native_video) | method | `MLXMultimodalLM._translate_messages_for_native_video(messages: list[dict], video_fps: float, video_max_frames: int) -> list[dict]` | Translate OpenAI API format messages to process_vision_info format. | [#L1697-L1832](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L1697-L1832) | | [`MLXMultimodalLM.generate`](#contract-vllm_mlx.models.mllm.MLXMultimodalLM.generate) | method | `MLXMultimodalLM.generate(prompt: str, images: list \| None = None, videos: list \| None = None, audio: list[str] \| None = None, max_tokens: int = 256, temperature: float = 0.7, top_p: float = 0.9, video_fps: float = DEFAULT_FPS, video_max_frames: int = MAX_FRAMES, use_cache: bool = True, **kwargs) -> MLLMOutput` | Generate text from multimodal input. | [#L1834-L2002](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L1834-L2002) | | [`MLXMultimodalLM.stream_generate`](#contract-vllm_mlx.models.mllm.MLXMultimodalLM.stream_generate) | method | `MLXMultimodalLM.stream_generate(prompt: str, images: list \| None = None, videos: list[str] \| None = None, audio: list[str] \| None = None, max_tokens: int = 256, temperature: float = 0.7, video_fps: float = DEFAULT_FPS, **kwargs) -> Iterator[str]` | Stream text generation for multimodal input. | [#L2004-L2093](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L2004-L2093) | | [`MLXMultimodalLM.chat`](#contract-vllm_mlx.models.mllm.MLXMultimodalLM.chat) | method | `MLXMultimodalLM.chat(messages: list[dict], max_tokens: int = 256, temperature: float = 0.7, **kwargs) -> MLLMOutput` | Chat with OpenAI-compatible message format. | [#L2095-L2487](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L2095-L2487) | | [`MLXMultimodalLM.stream_chat`](#contract-vllm_mlx.models.mllm.MLXMultimodalLM.stream_chat) | method | `MLXMultimodalLM.stream_chat(messages: list[dict], max_tokens: int = 256, temperature: float = 0.7, **kwargs) -> Iterator[MLLMOutput]` | Stream chat with OpenAI-compatible message format. | [#L2489-L2737](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L2489-L2737) | | [`MLXMultimodalLM.describe_image`](#contract-vllm_mlx.models.mllm.MLXMultimodalLM.describe_image) | method | `MLXMultimodalLM.describe_image(image: str, prompt: str = 'Describe this image in detail.', max_tokens: int = 512, **kwargs) -> str` | Convenience method to describe an image. | [#L2739-L2764](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L2739-L2764) | | [`MLXMultimodalLM.answer_about_image`](#contract-vllm_mlx.models.mllm.MLXMultimodalLM.answer_about_image) | method | `MLXMultimodalLM.answer_about_image(image: str, question: str, max_tokens: int = 256, **kwargs) -> str` | Answer a question about an image. | [#L2766-L2791](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L2766-L2791) | | [`MLXMultimodalLM.describe_video`](#contract-vllm_mlx.models.mllm.MLXMultimodalLM.describe_video) | method | `MLXMultimodalLM.describe_video(video: str \| dict, prompt: str = 'Describe what happens in this video.', fps: float = 2.0, max_frames: int = 32, max_tokens: int = 512, **kwargs) -> str` | Describe a video using frame extraction. | [#L2793-L2830](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L2793-L2830) | | [`MLXMultimodalLM.get_cache_stats`](#contract-vllm_mlx.models.mllm.MLXMultimodalLM.get_cache_stats) | method | `MLXMultimodalLM.get_cache_stats() -> dict` | Get MLLM cache statistics. | [#L2832-L2846](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L2832-L2846) | | [`MLXMultimodalLM.clear_cache`](#contract-vllm_mlx.models.mllm.MLXMultimodalLM.clear_cache) | method | `MLXMultimodalLM.clear_cache() -> None` | Clear the MLLM KV cache. | [#L2848-L2852](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L2848-L2852) | | [`MLXMultimodalLM.get_model_info`](#contract-vllm_mlx.models.mllm.MLXMultimodalLM.get_model_info) | method | `MLXMultimodalLM.get_model_info() -> dict` | Get information about the loaded model. | [#L2854-L2874](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L2854-L2874) | | [`MLXMultimodalLM.list_supported_model_families`](#contract-vllm_mlx.models.mllm.MLXMultimodalLM.list_supported_model_families) | method | `MLXMultimodalLM.list_supported_model_families() -> dict[str, str]` | List supported model families and their patterns. | [#L2877-L2897](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L2877-L2897) | | [`MLXMultimodalLM.is_mllm_model`](#contract-vllm_mlx.models.mllm.MLXMultimodalLM.is_mllm_model) | method | `MLXMultimodalLM.is_mllm_model(model_name: str) -> bool` | Check if a model name indicates an MLLM model. | [#L2900-L2934](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L2900-L2934) | | [`MLXMultimodalLM.__repr__`](#contract-vllm_mlx.models.mllm.MLXMultimodalLM.__repr__) | method | `MLXMultimodalLM.__repr__() -> str` | Method `MLXMultimodalLM.__repr__` returns `f''`. | [#L2936-L2938](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/models/mllm.py#L2936-L2938) |