Update test_sparse_attention.py

tests/unit/test_sparse_attention.py

@@ -232,6 +232,7 @@ def init_softmax_inputs(Z, H, M, N, scale, rho, block, dtype, dense_x=True, layo
 
 
 def _skip_on_cuda_compatability():
+    pytest.skip("Skip these tests for now until we get our docker image fixed.")
     if torch.cuda.get_device_capability()[0] != 7:
         pytest.skip("needs compute capability 7; v100")
     cuda_major = int(torch.version.cuda.split('.')[0]) * 10