support tests

Author: Devjiu

bitsandbytes/backends/triton/ops.py

@@ -59,7 +59,7 @@ def quantize_blockwise(A: torch.Tensor, code: torch.Tensor, blocksize: int) -> t
     triton_kernels.quantize_blockwise_triton(A, blocksize, code, blocks, absmax, out)
     out = out.reshape(A.shape)
 
-    return out, absmax
+    return out, absmax.float()
 
 
 def dequantize_blockwise(

tests/test_modules.py

@@ -287,6 +287,8 @@ def test_linear_kbit_fp32_bias(device, module):
 def test_kbit_backprop(device, module):
     if device == "cpu":
         pytest.xfail("Test is not yet supported on CPU")
+    if device == "xpu":
+        pytest.xfail("Missing int8_double_quant implementation XPU")
 
     b = 16
     dim1 = 36