fix ci

Signed-off-by: wangxiyuan <[email protected]>

Author: wangxiyuan

vllm_ascend/patch/worker/patch_common/patch_weight_loader.py

@@ -1,4 +1,3 @@
-
 import torch
 from torch.nn.parameter import Parameter
 from vllm.logger import init_logger

vllm_ascend/quantization/quant_config.py

@@ -33,7 +33,6 @@
 from vllm.model_executor.layers.quantization.kv_cache import BaseKVCacheMethod
 from vllm.model_executor.layers.vocab_parallel_embedding import (
     UnquantizedEmbeddingMethod, VocabParallelEmbedding)
-from vllm.model_executor.parameter import PerTensorScaleParameter
 from vllm.model_executor.utils import set_weight_attrs
 
 from vllm_ascend.distributed.parallel_state import (get_mlp_tp_group,
@@ -251,7 +250,6 @@ def create_weights(
         **extra_weight_attrs,
     ) -> None:
         output_size_per_partition = sum(output_partition_sizes)
-        weight_loader = extra_weight_attrs.get("weight_loader")
 
         weight_dict = self.quant_method.get_weight(input_size_per_partition,
                                                    output_size_per_partition,
@@ -264,8 +262,7 @@ def create_weights(
 
         pertensor_dict = self.quant_method.get_pertensor_param(params_dtype)
         for pertensor_name, pertensor_param in pertensor_dict.items():
-            param = PerTensorScaleParameter(data=pertensor_param,
-                                            weight_loader=weight_loader)
+            param = torch.nn.Parameter(pertensor_param, requires_grad=False)
             # disable warning
             param.ignore_warning = True
             layer.register_parameter(pertensor_name, param)