Convert formatting to use ruff instead of yapf + isort (#26247)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
This commit is contained in:
@@ -19,8 +19,9 @@ class QuantizeMethodBase(ABC):
|
||||
"""Base class for different quantized methods."""
|
||||
|
||||
@abstractmethod
|
||||
def create_weights(self, layer: torch.nn.Module, *weight_args,
|
||||
**extra_weight_attrs):
|
||||
def create_weights(
|
||||
self, layer: torch.nn.Module, *weight_args, **extra_weight_attrs
|
||||
):
|
||||
"""Create weights for a layer.
|
||||
|
||||
The weights will be set as attributes of the layer."""
|
||||
@@ -34,8 +35,7 @@ class QuantizeMethodBase(ABC):
|
||||
raise NotImplementedError
|
||||
|
||||
# Not required functions
|
||||
def embedding(self, layer: torch.nn.Module, *args,
|
||||
**kwargs) -> torch.Tensor:
|
||||
def embedding(self, layer: torch.nn.Module, *args, **kwargs) -> torch.Tensor:
|
||||
"""Gather embeddings in the layer based on indices in the input tensor.
|
||||
|
||||
Expects create_weights to have been called before on the layer."""
|
||||
@@ -49,19 +49,16 @@ class QuantizeMethodBase(ABC):
|
||||
return
|
||||
|
||||
|
||||
def method_has_implemented_embedding(
|
||||
method_class: type[QuantizeMethodBase]) -> bool:
|
||||
def method_has_implemented_embedding(method_class: type[QuantizeMethodBase]) -> bool:
|
||||
"""
|
||||
Not all quant methods have embedding implemented, so we need to check that
|
||||
it exists for our given method. We check this by making sure the function
|
||||
has been changed from the base implementation.
|
||||
"""
|
||||
base_embedding = inspect.getattr_static(QuantizeMethodBase, "embedding",
|
||||
None)
|
||||
base_embedding = inspect.getattr_static(QuantizeMethodBase, "embedding", None)
|
||||
class_embedding = inspect.getattr_static(method_class, "embedding", None)
|
||||
|
||||
return (class_embedding is not None
|
||||
and class_embedding is not base_embedding)
|
||||
return class_embedding is not None and class_embedding is not base_embedding
|
||||
|
||||
|
||||
class QuantizationConfig(ABC):
|
||||
@@ -107,12 +104,13 @@ class QuantizationConfig(ABC):
|
||||
|
||||
@classmethod
|
||||
def override_quantization_method(
|
||||
cls, hf_quant_cfg, user_quant) -> Optional[QuantizationMethods]:
|
||||
cls, hf_quant_cfg, user_quant
|
||||
) -> Optional[QuantizationMethods]:
|
||||
"""
|
||||
Detects if this quantization method can support a given checkpoint
|
||||
format by overriding the user specified quantization method --
|
||||
this method should only be overwritten by subclasses in exceptional
|
||||
circumstances
|
||||
Detects if this quantization method can support a given checkpoint
|
||||
format by overriding the user specified quantization method --
|
||||
this method should only be overwritten by subclasses in exceptional
|
||||
circumstances
|
||||
"""
|
||||
return None
|
||||
|
||||
@@ -122,12 +120,12 @@ class QuantizationConfig(ABC):
|
||||
for key in keys:
|
||||
if key in config:
|
||||
return config[key]
|
||||
raise ValueError(f"Cannot find any of {keys} in the model's "
|
||||
"quantization config.")
|
||||
raise ValueError(
|
||||
f"Cannot find any of {keys} in the model's quantization config."
|
||||
)
|
||||
|
||||
@staticmethod
|
||||
def get_from_keys_or(config: dict[str, Any], keys: list[str],
|
||||
default: Any) -> Any:
|
||||
def get_from_keys_or(config: dict[str, Any], keys: list[str], default: Any) -> Any:
|
||||
"""Get an optional value from the model's quantization config."""
|
||||
try:
|
||||
return QuantizationConfig.get_from_keys(config, keys)
|
||||
@@ -135,10 +133,11 @@ class QuantizationConfig(ABC):
|
||||
return default
|
||||
|
||||
@abstractmethod
|
||||
def get_quant_method(self, layer: torch.nn.Module,
|
||||
prefix: str) -> Optional[QuantizeMethodBase]:
|
||||
def get_quant_method(
|
||||
self, layer: torch.nn.Module, prefix: str
|
||||
) -> Optional[QuantizeMethodBase]:
|
||||
"""Get the quantize method to use for the quantized layer.
|
||||
|
||||
|
||||
Args:
|
||||
layer: The layer for the quant method.
|
||||
prefix: The full name of the layer in the state dict
|
||||
@@ -152,7 +151,8 @@ class QuantizationConfig(ABC):
|
||||
return None
|
||||
|
||||
def apply_vllm_mapper( # noqa: B027
|
||||
self, hf_to_vllm_mapper: "WeightsMapper"):
|
||||
self, hf_to_vllm_mapper: "WeightsMapper"
|
||||
):
|
||||
"""
|
||||
Interface for models to update module names referenced in
|
||||
quantization configs in order to reflect the vllm model structure
|
||||
|
||||
Reference in New Issue
Block a user