# `vllm_mlx.patches.qwen3_5_mllm`

Runtime patch for mlx-vlm's Qwen3.5 attention to support BatchKVCache.

[View the complete module source at #L1-L266](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/patches/qwen3_5_mllm.py#L1-L266).

## 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.patches.qwen3_5_mllm
    options:
      members:
        - logger
        - _cache_offset_to_int
        - _default_target_verify_linears
        - _default_target_verify_left_padded_attention
        - _normalize_position_inputs
        - _position_ids_for_offset
        - _kv_seq_len
        - _apply_rotary
        - _slice_attention_mask
        - _maybe_target_verify_attention
        - patch_qwen35_attention_for_batching
      filters: []
      show_if_no_docstring: true

## Complete contract reference

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

<details class="api-contract" id="contract-vllm_mlx.patches.qwen3_5_mllm._cache_offset_to_int" markdown="1">
<summary><code>vllm_mlx.patches.qwen3_5_mllm._cache_offset_to_int</code> · function</summary>

```python
vllm_mlx.patches.qwen3_5_mllm._cache_offset_to_int(cache) -> int
```

Extract cache offset as int, handling BatchKVCache mx.array offset.

**Parameters**

| Name | Type | Required | Default | Description |
| --- | --- | --- | --- | --- |
| `cache` | `not annotated` | `yes` | `none` | Required positional or keyword input. |

**Returns**

- Type: `int`
- Direct return expressions: `0`; `off`; `int(off.max().item()) if off.ndim > 0 else int(off.item())`; `int(off)`

**Exceptions and behavior**

Function `_cache_offset_to_int` calls `isinstance`, `int`, `off.max().item`, `off.max`; has 4 explicit return paths.
No direct `raise` statement appears in this definition.

[View source #L33-L42](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/patches/qwen3_5_mllm.py#L33-L42).

</details>

<details class="api-contract" id="contract-vllm_mlx.patches.qwen3_5_mllm._default_target_verify_linears" markdown="1">
<summary><code>vllm_mlx.patches.qwen3_5_mllm._default_target_verify_linears</code> · function</summary>

```python
vllm_mlx.patches.qwen3_5_mllm._default_target_verify_linears(linears, x, target_verify: bool) -> not annotated
```

Function `_default_target_verify_linears` calls `tuple`, `linear`; returns `tuple((linear(x) for linear in linears))`.

**Parameters**

| Name | Type | Required | Default | Description |
| --- | --- | --- | --- | --- |
| `linears` | `not annotated` | `yes` | `none` | Required positional or keyword input. |
| `x` | `not annotated` | `yes` | `none` | Required positional or keyword input. |
| `target_verify` | `bool` | `yes` | `none` | Required positional or keyword input. |

**Returns**

- Type: `not annotated`
- Direct return expressions: `tuple((linear(x) for linear in linears))`

**Exceptions and behavior**

Function `_default_target_verify_linears` calls `tuple`, `linear`; returns `tuple((linear(x) for linear in linears))`.
No direct `raise` statement appears in this definition.

[View source #L45-L46](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/patches/qwen3_5_mllm.py#L45-L46).

</details>

<details class="api-contract" id="contract-vllm_mlx.patches.qwen3_5_mllm._default_target_verify_left_padded_attention" markdown="1">
<summary><code>vllm_mlx.patches.qwen3_5_mllm._default_target_verify_left_padded_attention</code> · function</summary>

```python
vllm_mlx.patches.qwen3_5_mllm._default_target_verify_left_padded_attention(*args, **kwargs) -> not annotated
```

Function `_default_target_verify_left_padded_attention` returns `None`.

**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: `None`

**Exceptions and behavior**

Function `_default_target_verify_left_padded_attention` returns `None`.
No direct `raise` statement appears in this definition.

[View source #L49-L50](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/patches/qwen3_5_mllm.py#L49-L50).

</details>

<details class="api-contract" id="contract-vllm_mlx.patches.qwen3_5_mllm._normalize_position_inputs" markdown="1">
<summary><code>vllm_mlx.patches.qwen3_5_mllm._normalize_position_inputs</code> · function</summary>

```python
vllm_mlx.patches.qwen3_5_mllm._normalize_position_inputs(position_ids: Optional[mx.array], position_embeddings: Optional[tuple[mx.array, mx.array]], length: int) -> tuple[Optional[mx.array], Optional[tuple[mx.array, mx.array]]]
```

Function `_normalize_position_inputs` calls `logger.debug`; has 2 explicit return paths.

**Parameters**

| Name | Type | Required | Default | Description |
| --- | --- | --- | --- | --- |
| `position_ids` | `Optional[mx.array]` | `yes` | `none` | Required positional or keyword input. |
| `position_embeddings` | `Optional[tuple[mx.array, mx.array]]` | `yes` | `none` | Required positional or keyword input. |
| `length` | `int` | `yes` | `none` | Required positional or keyword input. |

**Returns**

- Type: `tuple[Optional[mx.array], Optional[tuple[mx.array, mx.array]]]`
- Direct return expressions: `(position_ids, position_embeddings)`; `(None, None)`

**Exceptions and behavior**

Function `_normalize_position_inputs` calls `logger.debug`; has 2 explicit return paths.
No direct `raise` statement appears in this definition.

[View source #L53-L65](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/patches/qwen3_5_mllm.py#L53-L65).

</details>

<details class="api-contract" id="contract-vllm_mlx.patches.qwen3_5_mllm._position_ids_for_offset" markdown="1">
<summary><code>vllm_mlx.patches.qwen3_5_mllm._position_ids_for_offset</code> · function</summary>

```python
vllm_mlx.patches.qwen3_5_mllm._position_ids_for_offset(offset: int, length: int) -> mx.array
```

Function `_position_ids_for_offset` calls `mx.arange`, `mx.expand_dims`, `mx.tile`; returns `mx.tile(position_ids, (3, 1, 1))`.

**Parameters**

| Name | Type | Required | Default | Description |
| --- | --- | --- | --- | --- |
| `offset` | `int` | `yes` | `none` | Required positional or keyword input. |
| `length` | `int` | `yes` | `none` | Required positional or keyword input. |

**Returns**

- Type: `mx.array`
- Direct return expressions: `mx.tile(position_ids, (3, 1, 1))`

**Exceptions and behavior**

Function `_position_ids_for_offset` calls `mx.arange`, `mx.expand_dims`, `mx.tile`; returns `mx.tile(position_ids, (3, 1, 1))`.
No direct `raise` statement appears in this definition.

[View source #L68-L71](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/patches/qwen3_5_mllm.py#L68-L71).

</details>

<details class="api-contract" id="contract-vllm_mlx.patches.qwen3_5_mllm._kv_seq_len" markdown="1">
<summary><code>vllm_mlx.patches.qwen3_5_mllm._kv_seq_len</code> · function</summary>

```python
vllm_mlx.patches.qwen3_5_mllm._kv_seq_len(keys: mx.array, cache: Optional[Any], offset: int) -> int
```

Function `_kv_seq_len` returns `length + offset + 1 if cache is not None else length`.

**Parameters**

| Name | Type | Required | Default | Description |
| --- | --- | --- | --- | --- |
| `keys` | `mx.array` | `yes` | `none` | Required positional or keyword input. |
| `cache` | `Optional[Any]` | `yes` | `none` | Required positional or keyword input. |
| `offset` | `int` | `yes` | `none` | Required positional or keyword input. |

**Returns**

- Type: `int`
- Direct return expressions: `length + offset + 1 if cache is not None else length`

**Exceptions and behavior**

Function `_kv_seq_len` returns `length + offset + 1 if cache is not None else length`.
No direct `raise` statement appears in this definition.

[View source #L74-L76](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/patches/qwen3_5_mllm.py#L74-L76).

</details>

<details class="api-contract" id="contract-vllm_mlx.patches.qwen3_5_mllm._apply_rotary" markdown="1">
<summary><code>vllm_mlx.patches.qwen3_5_mllm._apply_rotary</code> · function</summary>

```python
vllm_mlx.patches.qwen3_5_mllm._apply_rotary(attention, queries: mx.array, keys: mx.array, values: mx.array, position_ids: mx.array, position_embeddings: Optional[tuple[mx.array, mx.array]], apply_multimodal_rotary_pos_emb) -> tuple[mx.array, mx.array]
```

Function `_apply_rotary` calls `apply_multimodal_rotary_pos_emb`, `hasattr`, `attention.rotary_emb.apply_rotary`, `attention.rotary_emb`; has 2 explicit return paths.

**Parameters**

| Name | Type | Required | Default | Description |
| --- | --- | --- | --- | --- |
| `attention` | `not annotated` | `yes` | `none` | Required positional or keyword input. |
| `queries` | `mx.array` | `yes` | `none` | Required positional or keyword input. |
| `keys` | `mx.array` | `yes` | `none` | Required positional or keyword input. |
| `values` | `mx.array` | `yes` | `none` | Required positional or keyword input. |
| `position_ids` | `mx.array` | `yes` | `none` | Required positional or keyword input. |
| `position_embeddings` | `Optional[tuple[mx.array, mx.array]]` | `yes` | `none` | Required positional or keyword input. |
| `apply_multimodal_rotary_pos_emb` | `not annotated` | `yes` | `none` | Required positional or keyword input. |

**Returns**

- Type: `tuple[mx.array, mx.array]`
- Direct return expressions: `apply_multimodal_rotary_pos_emb(queries, keys, cos, sin)`; `attention.rotary_emb.apply_rotary(queries, keys, position_ids, unsqueeze_dim=1)`

**Exceptions and behavior**

Function `_apply_rotary` calls `apply_multimodal_rotary_pos_emb`, `hasattr`, `attention.rotary_emb.apply_rotary`, `attention.rotary_emb`; has 2 explicit return paths.
No direct `raise` statement appears in this definition.

[View source #L79-L101](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/patches/qwen3_5_mllm.py#L79-L101).

</details>

<details class="api-contract" id="contract-vllm_mlx.patches.qwen3_5_mllm._slice_attention_mask" markdown="1">
<summary><code>vllm_mlx.patches.qwen3_5_mllm._slice_attention_mask</code> · function</summary>

```python
vllm_mlx.patches.qwen3_5_mllm._slice_attention_mask(mask: Optional[mx.array], cache: Optional[Any], kv_seq_len: int, length: int) -> Optional[mx.array]
```

Function `_slice_attention_mask` calls `isinstance`, `hasattr`, `int`, `kv_seq_len.max().item`; has 2 explicit return paths.

**Parameters**

| Name | Type | Required | Default | Description |
| --- | --- | --- | --- | --- |
| `mask` | `Optional[mx.array]` | `yes` | `none` | Required positional or keyword input. |
| `cache` | `Optional[Any]` | `yes` | `none` | Required positional or keyword input. |
| `kv_seq_len` | `int` | `yes` | `none` | Required positional or keyword input. |
| `length` | `int` | `yes` | `none` | Required positional or keyword input. |

**Returns**

- Type: `Optional[mx.array]`
- Direct return expressions: `mask`; `mask[..., :int(kv_seq_len)]`

**Exceptions and behavior**

Function `_slice_attention_mask` calls `isinstance`, `hasattr`, `int`, `kv_seq_len.max().item`; has 2 explicit return paths.
No direct `raise` statement appears in this definition.

[View source #L104-L116](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/patches/qwen3_5_mllm.py#L104-L116).

</details>

<details class="api-contract" id="contract-vllm_mlx.patches.qwen3_5_mllm._maybe_target_verify_attention" markdown="1">
<summary><code>vllm_mlx.patches.qwen3_5_mllm._maybe_target_verify_attention</code> · function</summary>

```python
vllm_mlx.patches.qwen3_5_mllm._maybe_target_verify_attention(queries: mx.array, keys: mx.array, values: mx.array, *, cache: Optional[Any], mask: Optional[mx.array], scale: float, target_verify: bool, length: int, left_padded_decode: bool, target_verify_left_padded_attention) -> Optional[mx.array]
```

Function `_maybe_target_verify_attention` calls `target_verify_left_padded_attention`; has 2 explicit return paths.

**Parameters**

| Name | Type | Required | Default | Description |
| --- | --- | --- | --- | --- |
| `queries` | `mx.array` | `yes` | `none` | Required positional or keyword input. |
| `keys` | `mx.array` | `yes` | `none` | Required positional or keyword input. |
| `values` | `mx.array` | `yes` | `none` | Required positional or keyword input. |
| `cache` | `Optional[Any]` | `yes` | `none` | Required keyword-only input. |
| `mask` | `Optional[mx.array]` | `yes` | `none` | Required keyword-only input. |
| `scale` | `float` | `yes` | `none` | Required keyword-only input. |
| `target_verify` | `bool` | `yes` | `none` | Required keyword-only input. |
| `length` | `int` | `yes` | `none` | Required keyword-only input. |
| `left_padded_decode` | `bool` | `yes` | `none` | Required keyword-only input. |
| `target_verify_left_padded_attention` | `not annotated` | `yes` | `none` | Required keyword-only input. |

**Returns**

- Type: `Optional[mx.array]`
- Direct return expressions: `None`; `target_verify_left_padded_attention(queries, keys, values, cache=cache, scale=scale, mask=mask)`

**Exceptions and behavior**

Function `_maybe_target_verify_attention` calls `target_verify_left_padded_attention`; has 2 explicit return paths.
No direct `raise` statement appears in this definition.

[View source #L119-L141](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/patches/qwen3_5_mllm.py#L119-L141).

</details>

<details class="api-contract" id="contract-vllm_mlx.patches.qwen3_5_mllm.patch_qwen35_attention_for_batching" markdown="1">
<summary><code>vllm_mlx.patches.qwen3_5_mllm.patch_qwen35_attention_for_batching</code> · function</summary>

```python
vllm_mlx.patches.qwen3_5_mllm.patch_qwen35_attention_for_batching() -> bool
```

Monkey-patch Qwen3_5Attention.__call__ to handle BatchKVCache.

**Parameters**

This callable has no explicit inputs.

**Returns**

- Type: `bool`
- Direct return expressions: `False`; `True`

**Exceptions and behavior**

Function `patch_qwen35_attention_for_batching` calls `importlib.import_module`, `logger.debug`, `getattr`, `setattr`; has 2 explicit return paths.
No direct `raise` statement appears in this definition.

[View source #L144-L266](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/patches/qwen3_5_mllm.py#L144-L266).

</details>

<details class="api-contract" id="contract-vllm_mlx.patches.qwen3_5_mllm.patch_qwen35_attention_for_batching._patched_call" markdown="1">
<summary><code>vllm_mlx.patches.qwen3_5_mllm.patch_qwen35_attention_for_batching._patched_call</code> · nested function</summary>

```python
vllm_mlx.patches.qwen3_5_mllm.patch_qwen35_attention_for_batching._patched_call(x: mx.array, mask: Optional[mx.array] = None, cache: Optional[Any] = None, position_ids: Optional[mx.array] = None, position_embeddings: Optional[tuple[mx.array, mx.array]] = None, target_verify: bool = False) -> mx.array
```

Nested Function `patch_qwen35_attention_for_batching._patched_call` calls `target_verify_linears`, `mx.split`, `q_proj_output.reshape`, `gate.reshape`; returns `self.o_proj(output * mx.sigmoid(gate))`.

**Parameters**

| Name | Type | Required | Default | Description |
| --- | --- | --- | --- | --- |
| `x` | `mx.array` | `yes` | `none` | Required positional or keyword input. |
| `mask` | `Optional[mx.array]` | `no` | `None` | Optional positional or keyword input; defaults to `None`. |
| `cache` | `Optional[Any]` | `no` | `None` | Optional positional or keyword input; defaults to `None`. |
| `position_ids` | `Optional[mx.array]` | `no` | `None` | Optional positional or keyword input; defaults to `None`. |
| `position_embeddings` | `Optional[tuple[mx.array, mx.array]]` | `no` | `None` | Optional positional or keyword input; defaults to `None`. |
| `target_verify` | `bool` | `no` | `False` | Optional positional or keyword input; defaults to `False`. |

**Returns**

- Type: `mx.array`
- Direct return expressions: `self.o_proj(output * mx.sigmoid(gate))`

**Exceptions and behavior**

Nested Function `patch_qwen35_attention_for_batching._patched_call` calls `target_verify_linears`, `mx.split`, `q_proj_output.reshape`, `gate.reshape`; returns `self.o_proj(output * mx.sigmoid(gate))`.
No direct `raise` statement appears in this definition.

[View source #L174-L261](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/patches/qwen3_5_mllm.py#L174-L261).

</details>

## Complete symbol map

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

| Symbol | Kind | Signature and inputs | What it does | Source |
| --- | --- | --- | --- | --- |
| [`_cache_offset_to_int`](#contract-vllm_mlx.patches.qwen3_5_mllm._cache_offset_to_int) | function | `_cache_offset_to_int(cache) -> int` | Extract cache offset as int, handling BatchKVCache mx.array offset. | [#L33-L42](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/patches/qwen3_5_mllm.py#L33-L42) |
| [`_default_target_verify_linears`](#contract-vllm_mlx.patches.qwen3_5_mllm._default_target_verify_linears) | function | `_default_target_verify_linears(linears, x, target_verify: bool) -> not annotated` | Function `_default_target_verify_linears` calls `tuple`, `linear`; returns `tuple((linear(x) for linear in linears))`. | [#L45-L46](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/patches/qwen3_5_mllm.py#L45-L46) |
| [`_default_target_verify_left_padded_attention`](#contract-vllm_mlx.patches.qwen3_5_mllm._default_target_verify_left_padded_attention) | function | `_default_target_verify_left_padded_attention(*args, **kwargs) -> not annotated` | Function `_default_target_verify_left_padded_attention` returns `None`. | [#L49-L50](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/patches/qwen3_5_mllm.py#L49-L50) |
| [`_normalize_position_inputs`](#contract-vllm_mlx.patches.qwen3_5_mllm._normalize_position_inputs) | function | `_normalize_position_inputs(position_ids: Optional[mx.array], position_embeddings: Optional[tuple[mx.array, mx.array]], length: int) -> tuple[Optional[mx.array], Optional[tuple[mx.array, mx.array]]]` | Function `_normalize_position_inputs` calls `logger.debug`; has 2 explicit return paths. | [#L53-L65](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/patches/qwen3_5_mllm.py#L53-L65) |
| [`_position_ids_for_offset`](#contract-vllm_mlx.patches.qwen3_5_mllm._position_ids_for_offset) | function | `_position_ids_for_offset(offset: int, length: int) -> mx.array` | Function `_position_ids_for_offset` calls `mx.arange`, `mx.expand_dims`, `mx.tile`; returns `mx.tile(position_ids, (3, 1, 1))`. | [#L68-L71](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/patches/qwen3_5_mllm.py#L68-L71) |
| [`_kv_seq_len`](#contract-vllm_mlx.patches.qwen3_5_mllm._kv_seq_len) | function | `_kv_seq_len(keys: mx.array, cache: Optional[Any], offset: int) -> int` | Function `_kv_seq_len` returns `length + offset + 1 if cache is not None else length`. | [#L74-L76](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/patches/qwen3_5_mllm.py#L74-L76) |
| [`_apply_rotary`](#contract-vllm_mlx.patches.qwen3_5_mllm._apply_rotary) | function | `_apply_rotary(attention, queries: mx.array, keys: mx.array, values: mx.array, position_ids: mx.array, position_embeddings: Optional[tuple[mx.array, mx.array]], apply_multimodal_rotary_pos_emb) -> tuple[mx.array, mx.array]` | Function `_apply_rotary` calls `apply_multimodal_rotary_pos_emb`, `hasattr`, `attention.rotary_emb.apply_rotary`, `attention.rotary_emb`; has 2 explicit return paths. | [#L79-L101](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/patches/qwen3_5_mllm.py#L79-L101) |
| [`_slice_attention_mask`](#contract-vllm_mlx.patches.qwen3_5_mllm._slice_attention_mask) | function | `_slice_attention_mask(mask: Optional[mx.array], cache: Optional[Any], kv_seq_len: int, length: int) -> Optional[mx.array]` | Function `_slice_attention_mask` calls `isinstance`, `hasattr`, `int`, `kv_seq_len.max().item`; has 2 explicit return paths. | [#L104-L116](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/patches/qwen3_5_mllm.py#L104-L116) |
| [`_maybe_target_verify_attention`](#contract-vllm_mlx.patches.qwen3_5_mllm._maybe_target_verify_attention) | function | `_maybe_target_verify_attention(queries: mx.array, keys: mx.array, values: mx.array, *, cache: Optional[Any], mask: Optional[mx.array], scale: float, target_verify: bool, length: int, left_padded_decode: bool, target_verify_left_padded_attention) -> Optional[mx.array]` | Function `_maybe_target_verify_attention` calls `target_verify_left_padded_attention`; has 2 explicit return paths. | [#L119-L141](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/patches/qwen3_5_mllm.py#L119-L141) |
| [`patch_qwen35_attention_for_batching`](#contract-vllm_mlx.patches.qwen3_5_mllm.patch_qwen35_attention_for_batching) | function | `patch_qwen35_attention_for_batching() -> bool` | Monkey-patch Qwen3_5Attention.__call__ to handle BatchKVCache. | [#L144-L266](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/patches/qwen3_5_mllm.py#L144-L266) |
| [`patch_qwen35_attention_for_batching._patched_call`](#contract-vllm_mlx.patches.qwen3_5_mllm.patch_qwen35_attention_for_batching._patched_call) | nested function | `patch_qwen35_attention_for_batching._patched_call(x: mx.array, mask: Optional[mx.array] = None, cache: Optional[Any] = None, position_ids: Optional[mx.array] = None, position_embeddings: Optional[tuple[mx.array, mx.array]] = None, target_verify: bool = False) -> mx.array` | Nested Function `patch_qwen35_attention_for_batching._patched_call` calls `target_verify_linears`, `mx.split`, `q_proj_output.reshape`, `gate.reshape`; returns `self.o_proj(output * mx.sigmoid(gate))`. | [#L174-L261](https://github.com/waybarrios/vllm-mlx/blob/a69d47912bcb21d8fe04d48f75fa896b620ffcfa/vllm_mlx/patches/qwen3_5_mllm.py#L174-L261) |