Keep the FACTO pow exponent representable in float32 (pytorch#24179)

Summary:

`pow.Tensor_Scalar`'s `exponent` fell into `facto_testcase_gen`'s generic scalar branch, `Gt(0)` and `Le(2)`. The open lower bound makes `nextup(0) = 5e-324` an edge value. That value flushes to 0 when a float32 kernel reads it, so `0 ** 5e-324` (0 in eager, computed with a double exponent) becomes `0 ** 0 = 1` on device. The exponent now gets its own lower bound of `torch.finfo(torch.float32).tiny`. Integer exponents are unchanged (≥ 1), and the upper bound stays 2.

Authored with Claude Code.

Reviewed By: DrJessop

Differential Revision: D127746756

Pull Request resolved: pytorch#24179

Author: aliafzal

backends/cadence/utils/facto_util.py

@@ -518,6 +518,17 @@ def facto_testcase_gen(  # noqa: C901
                 spec.inspec[index].constraints.extend(
                     [cp.Value.Ge(lambda deps, _: deps[1])]
                 )
+            elif in_spec.name == "exponent" and op_name == "pow.Tensor_Scalar":
+                # A Gt(0) bound makes nextup(0) = 5e-324 an edge value, which
+                # flushes to 0 in float32 kernels and turns 0 ** e into 0 ** 0.
+                spec.inspec[index].constraints.extend(
+                    [
+                        cp.Value.Ge(
+                            lambda deps, dtype: torch.finfo(torch.float32).tiny
+                        ),
+                        cp.Value.Le(lambda deps, dtype: 2),
+                    ]
+                )
             elif in_spec.name == "negative_slope" and op_name == "leaky_relu.default":
                 # For leaky_relu, negative_slope should be in typical range (0, 1]
                 spec.inspec[index].constraints.extend(