update

Author: DN6

src/diffusers/quantizers/gguf/gguf_quantizer.py

@@ -37,7 +37,7 @@ def __init__(self, quantization_config, **kwargs):
         super().__init__(quantization_config, **kwargs)
 
         self.compute_dtype = quantization_config.compute_dtype
-        self.pre_quantized = True
+        self.pre_quantized = quantization_config.pre_quantized
 
     def validate_environment(self, *args, **kwargs):
         if not is_accelerate_available() or is_accelerate_version("<", "0.26.0"):

src/diffusers/quantizers/quantization_config.py

@@ -397,6 +397,7 @@ def __init__(self, compute_dtype=None, quant_storage=None):
         self.quant_method = QuantizationMethod.GGUF
         self.compute_dtype = compute_dtype
         self.quant_storage = quant_storage
+        self.pre_quantized = True
 
         if self.compute_dtype is None:
             self.compute_dtype = torch.float32