Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
This commit is contained in:
@@ -1,7 +1,7 @@
|
||||
# SPDX-License-Identifier: Apache-2.0
|
||||
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
|
||||
|
||||
from typing import Any, Optional, Union
|
||||
from typing import Any, Union
|
||||
|
||||
import torch
|
||||
|
||||
@@ -34,7 +34,7 @@ class AWQConfig(QuantizationConfig):
|
||||
weight_bits: int,
|
||||
group_size: int,
|
||||
zero_point: bool,
|
||||
modules_to_not_convert: Optional[list[str]] = None,
|
||||
modules_to_not_convert: list[str] | None = None,
|
||||
) -> None:
|
||||
super().__init__()
|
||||
self.weight_bits = weight_bits
|
||||
@@ -88,7 +88,7 @@ class AWQConfig(QuantizationConfig):
|
||||
|
||||
def get_quant_method(
|
||||
self, layer: torch.nn.Module, prefix: str
|
||||
) -> Optional[Union["LinearMethodBase", "QuantizeMethodBase"]]:
|
||||
) -> Union["LinearMethodBase", "QuantizeMethodBase"] | None:
|
||||
if isinstance(layer, LinearBase):
|
||||
if is_layer_skipped_awq(prefix, self.modules_to_not_convert):
|
||||
return UnquantizedLinearMethod()
|
||||
@@ -227,7 +227,7 @@ class AWQLinearMethod(LinearMethodBase):
|
||||
self,
|
||||
layer: torch.nn.Module,
|
||||
x: torch.Tensor,
|
||||
bias: Optional[torch.Tensor] = None,
|
||||
bias: torch.Tensor | None = None,
|
||||
) -> torch.Tensor:
|
||||
qweight = layer.qweight
|
||||
scales = layer.scales
|
||||
|
||||
Reference in New Issue
Block a user