Improve configs - ModelConfig (#17130)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
This commit is contained in:
@@ -7,6 +7,7 @@ import torch
|
||||
from vllm import _custom_ops as ops
|
||||
from vllm.model_executor.layers.linear import (LinearBase, LinearMethodBase,
|
||||
UnquantizedLinearMethod)
|
||||
from vllm.model_executor.layers.quantization import QuantizationMethods
|
||||
from vllm.model_executor.layers.quantization.base_config import (
|
||||
QuantizationConfig)
|
||||
from vllm.model_executor.parameter import (GroupQuantScaleParameter,
|
||||
@@ -44,7 +45,7 @@ class AWQConfig(QuantizationConfig):
|
||||
f"zero_point={self.zero_point}, "
|
||||
f"modules_to_not_convert={self.modules_to_not_convert})")
|
||||
|
||||
def get_name(self) -> str:
|
||||
def get_name(self) -> QuantizationMethods:
|
||||
return "awq"
|
||||
|
||||
def get_supported_act_dtypes(self) -> List[torch.dtype]:
|
||||
|
||||
Reference in New Issue
Block a user