[CPU] Disable oneDNN linear on non-x86 platforms (#25166)

Signed-off-by: jiang1.li <jiang1.li@intel.com>

vllm/model_executor/layers/utils.py

@@ -7,7 +7,7 @@ import torch
 
 from vllm import _custom_ops as ops
 from vllm import envs
-from vllm.platforms import current_platform
+from vllm.platforms import CpuArchEnum, current_platform
 from vllm.utils import direct_register_custom_op
 
 
@@ -167,7 +167,8 @@ def dispatch_cpu_unquantized_gemm(
         if remove_weight:
             layer.weight = torch.nn.Parameter(torch.empty(0),
                                               requires_grad=False)
-    elif ops._supports_onednn:
+    elif (ops._supports_onednn
+          and current_platform.get_cpu_architecture() == CpuArchEnum.X86):
         origin_weight = layer.weight
         if remove_weight:
             layer.weight = torch.nn.Parameter(torch.empty(0),