diff --git a/vllm/config.py b/vllm/config.py
index 085060535e2b..6cec97a5f11b 100644
--- a/vllm/config.py
+++ b/vllm/config.py
@@ -304,7 +304,7 @@ class ModelConfig:
     - 25.6k -> 25,600"""
     spec_target_max_model_len: Optional[int] = None
     """Specify the maximum length for spec decoding draft models."""
-    quantization: Optional[QuantizationMethods] = None
+    quantization: SkipValidation[Optional[QuantizationMethods]] = None
     """Method used to quantize the weights. If `None`, we first check the
     `quantization_config` attribute in the model config file. If that is
     `None`, we assume the model weights are not quantized and use `dtype` to
@@ -2231,7 +2231,7 @@ Device = Literal["auto", "cuda", "neuron", "cpu", "tpu", "xpu", "hpu"]
 class DeviceConfig:
     """Configuration for the device to use for vLLM execution."""
 
-    device: Union[Device, torch.device] = "auto"
+    device: SkipValidation[Union[Device, torch.device]] = "auto"
     """Device type for vLLM execution.
     This parameter is deprecated and will be 
     removed in a future release.