[xpu][test] Port 2 test/quantization_{qat, quant_api} UT files to intel XPU (#3351)

* port 2 files to intel XPU

* port 2 files to intel XPU

* update

* update

Author: zxd1997066

test/quantization/test_qat.py

@@ -98,12 +98,14 @@
 )
 from torchao.utils import (
     _is_fbgemm_gpu_genai_available,
+    get_current_accelerator_device,
     is_fbcode,
     is_sm_at_least_89,
 )
 
 # TODO: put this in a common test utils file
 _CUDA_IS_AVAILABLE = torch.cuda.is_available()
+_DEVICE = get_current_accelerator_device()
 
 
 class Sub(torch.nn.Module):
@@ -347,7 +349,7 @@ def _set_ptq_weight(
                 group_size,
             )
             q_weight = torch.ops.aten._convert_weight_to_int4pack(
-                q_weight.to("cuda"),
+                q_weight.to(_DEVICE),
                 qat_linear.inner_k_tiles,
             )
             ptq_linear.weight = q_weight
@@ -600,13 +602,13 @@ def _assert_close_4w(self, val, ref):
         print(mean_err)
         self.assertTrue(mean_err < 0.05)
 
-    @unittest.skipIf(not _CUDA_IS_AVAILABLE, "skipping when cuda is not available")
+    @unittest.skipIf(_DEVICE is None, "skipping when gpu is not available")
     def test_qat_4w_primitives(self):
         n_bit = 4
         group_size = 32
         inner_k_tiles = 8
         scales_precision = torch.bfloat16
-        device = torch.device("cuda")
+        device = torch.device(_DEVICE)
         dtype = torch.bfloat16
         torch.manual_seed(self.SEED)
         x = torch.randn(100, 256, dtype=dtype, device=device)
@@ -699,7 +701,7 @@ def test_qat_4w_quantizer(self):
 
         group_size = 32
         inner_k_tiles = 8
-        device = torch.device("cuda")
+        device = torch.device(_DEVICE)
         dtype = torch.bfloat16
         torch.manual_seed(self.SEED)
         m = M().to(device).to(dtype)