add permute cols opcheck

tests/kernels/test_permute_cols.py

@@ -0,0 +1,15 @@
+import pytest
+import torch
+
+from tests.kernels.utils import opcheck
+from vllm._custom_ops import permute_cols
+
+
+@pytest.mark.parametrize('shape', [(1, 512), (544, 4096), (67, 8192)])
+@pytest.mark.parametrize('dtype', [torch.bfloat16, torch.float16])
+def test_permute_cols(shape, dtype):
+    x = torch.randn(shape, dtype=dtype).cuda()
+    perm = torch.randperm(x.shape[1]).to(torch.int).cuda()
+    opcheck(torch.ops._C.permute_cols, (x, perm))
+    y = permute_cols(x, perm)
+    torch.testing.assert_close(y, x[:, perm])

vllm/_custom_ops.py

@@ -576,6 +576,18 @@ def machete_prepack_B(b_q_weight: torch.Tensor,
     return torch.ops._C.machete_prepack_B(b_q_weight, b_type)
 
 
+# TODO: has to be a better way to do this
+try:
+    torch.ops._C.permute_cols  # noqa B018
+
+    @torch.library.register_fake("_C::permute_cols")
+    def _permute_cols_fake(a: torch.Tensor,
+                           perm: torch.Tensor) -> torch.Tensor:
+        return torch.empty_like(a)
+except Exception:
+    pass
+
+
 def permute_cols(a: torch.Tensor, perm: torch.Tensor) -> torch.Tensor:
     return torch.ops._C.permute_cols(a, perm)