20231088/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

[Misc] Remove outdated init protocols (#10655)

Browse Source 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
This commit is contained in:
Cyrus Leung 2024-11-26 14:55:00 +08:00 committed by GitHub
parent 9a88f89799
commit 940635343a
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 1 additions and 31 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

30
vllm/model_executor/models/interfaces.py
View File

@ -10,7 +10,6 @@ from vllm.utils import supports_kw
from .interfaces_base import is_embedding_model
if TYPE_CHECKING:
from vllm.config import LoRAConfig, MultiModalConfig, SchedulerConfig
from vllm.sequence import IntermediateTensors
logger = init_logger(__name__)
@ -29,9 +28,6 @@ class SupportsMultiModal(Protocol):
MRO of your model class.
"""
def __init__(self, *, multimodal_config: "MultiModalConfig") -> None:
...
# We can't use runtime_checkable with ClassVar for issubclass checks
# so we need to treat the class as an instance and use isinstance instead
@ -39,9 +35,6 @@ class SupportsMultiModal(Protocol):
class _SupportsMultiModalType(Protocol):
supports_multimodal: Literal[True]
def __call__(self, *, multimodal_config: "MultiModalConfig") -> None:
...
@overload
def supports_multimodal(
@ -81,10 +74,6 @@ class SupportsLoRA(Protocol):
embedding_modules: ClassVar[Dict[str, str]]
embedding_padding_modules: ClassVar[List[str]]
# lora_config is None when LoRA is not enabled
def __init__(self, *, lora_config: Optional["LoRAConfig"] = None) -> None:
...
# We can't use runtime_checkable with ClassVar for issubclass checks
# so we need to treat the class as an instance and use isinstance instead
@ -97,9 +86,6 @@ class _SupportsLoRAType(Protocol):
embedding_modules: Dict[str, str]
embedding_padding_modules: List[str]
def __call__(self, *, lora_config: Optional["LoRAConfig"] = None) -> None:
...
@overload
def supports_lora(model: Type[object]) -> TypeIs[Type[SupportsLoRA]]:
@ -276,21 +262,11 @@ class HasInnerState(Protocol):
for max_num_seqs, etc. True for e.g. both Mamba and Jamba.
"""
def __init__(self,
*,
scheduler_config: Optional["SchedulerConfig"] = None) -> None:
...
@runtime_checkable
class _HasInnerStateType(Protocol):
has_inner_state: ClassVar[Literal[True]]
def __init__(self,
*,
scheduler_config: Optional["SchedulerConfig"] = None) -> None:
...
@overload
def has_inner_state(model: object) -> TypeIs[HasInnerState]:
@ -323,17 +299,11 @@ class IsAttentionFree(Protocol):
True for Mamba but not Jamba.
"""
def __init__(self) -> None:
...
@runtime_checkable
class _IsAttentionFreeType(Protocol):
is_attention_free: ClassVar[Literal[True]]
def __init__(self) -> None:
...
@overload
def is_attention_free(model: object) -> TypeIs[IsAttentionFree]:

2
vllm/model_executor/models/interfaces_base.py
View File

@ -71,7 +71,7 @@ def _check_vllm_model_forward(model: Union[Type[object], object]) -> bool:
and issubclass(model, nn.Module)):
logger.warning(
"The model (%s) is missing "
"vLLM-specific keywords from its initializer: %s",
"vLLM-specific keywords from its `forward` method: %s",
model,
missing_kws,
)