vllm.v1.attention.backends.registry ¶
Attention backend registry
AttentionBackendEnum ¶
Bases: Enum
Enumeration of all supported attention backends.
The enum value is the default class path, but this can be overridden at runtime using register_backend().
To get the actual backend class (respecting overrides), use: backend.get_class()
Source code in vllm/v1/attention/backends/registry.py
34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 | |
clear_override ¶
get_class ¶
get_class() -> type[AttentionBackend]
Get the backend class (respects overrides).
Returns:
| Type | Description |
|---|---|
type[AttentionBackend] | The backend class |
Raises:
| Type | Description |
|---|---|
ImportError | If the backend class cannot be imported |
ValueError | If Backend.CUSTOM is used without being registered |
Source code in vllm/v1/attention/backends/registry.py
get_path ¶
Get the class path for this backend (respects overrides).
Returns:
| Type | Description |
|---|---|
str | The fully qualified class path string |
Raises:
| Type | Description |
|---|---|
ValueError | If Backend.CUSTOM is used without being registered |
Source code in vllm/v1/attention/backends/registry.py
MambaAttentionBackendEnum ¶
Bases: Enum
Enumeration of all supported mamba attention backends.
The enum value is the default class path, but this can be overridden at runtime using register_backend().
To get the actual backend class (respecting overrides), use: backend.get_class()
Source code in vllm/v1/attention/backends/registry.py
clear_override ¶
get_class ¶
get_class() -> type[AttentionBackend]
Get the backend class (respects overrides).
Returns:
| Type | Description |
|---|---|
type[AttentionBackend] | The backend class |
Raises:
| Type | Description |
|---|---|
ImportError | If the backend class cannot be imported |
ValueError | If Backend.CUSTOM is used without being registered |
Source code in vllm/v1/attention/backends/registry.py
get_path ¶
Get the class path for this backend (respects overrides).
Returns:
| Type | Description |
|---|---|
str | The fully qualified class path string |
Raises:
| Type | Description |
|---|---|
ValueError | If Backend.CUSTOM is used without being registered |
Source code in vllm/v1/attention/backends/registry.py
_AttentionBackendEnumMeta ¶
Bases: EnumMeta
Metaclass for AttentionBackendEnum to provide better error messages.
Source code in vllm/v1/attention/backends/registry.py
__getitem__ ¶
__getitem__(name: str)
Get backend by name with helpful error messages.
Source code in vllm/v1/attention/backends/registry.py
register_backend ¶
register_backend(
backend: AttentionBackendEnum
| MambaAttentionBackendEnum,
class_path: str | None = None,
is_mamba: bool = False,
) -> Callable[[type], type]
Register or override a backend implementation.
Parameters:
| Name | Type | Description | Default |
|---|---|---|---|
backend | AttentionBackendEnum | MambaAttentionBackendEnum | The AttentionBackendEnum member to register | required |
class_path | str | None | Optional class path. If not provided and used as decorator, will be auto-generated from the class. | None |
Returns:
| Type | Description |
|---|---|
Callable[[type], type] | Decorator function if class_path is None, otherwise a no-op |
Examples:
Override an existing attention backend¶
@register_backend(AttentionBackendEnum.FLASH_ATTN) class MyCustomFlashAttn: ...
Override an existing mamba attention backend¶
@register_backend(MambaAttentionBackendEnum.LINEAR, is_mamba=True) class MyCustomMambaAttn: ...
Register a custom third-party attention backend¶
@register_backend(AttentionBackendEnum.CUSTOM) class MyCustomBackend: ...
Direct registration¶
register_backend( AttentionBackendEnum.CUSTOM, "my.module.MyCustomBackend" )