Align mlx::core::max op nan propagation with NumPy (#2339)

* Make max op NaN propagation rules align with numpy

* Adding benchmarks and testing for max op nanpropagation

* Pre-commit formatting

* Fix max complex64 nan propagation and add test

* Improve the cpp unittest

* Only check nans on non-integral types in simd_reduce_impl.

* Cleanup using namespace alias

* Add cpu Max nanpropagation. Fix a small fib in cpu max dispatch data types for int8/int16.

* Make the max nanpropagation test more meaningful for integer types

* Remove tuple unpacking syntax to comply with earlier python versions. Add cuda skip to nanpropagation tests, fix cuda implementation in a separate PR.

benchmarks/python/single_ops.py

@@ -51,6 +51,13 @@ def time_maximum():
     time_fn(mx.maximum, a, b)
 
 
+def time_max():
+    a = mx.random.uniform(shape=(32, 1024, 1024))
+    a[1, 1] = mx.nan
+    mx.eval(a)
+    time_fn(mx.max, a, 0)
+
+
 def time_negative():
     a = mx.random.uniform(shape=(10000, 1000))
     mx.eval(a)
@@ -108,6 +115,7 @@ if __name__ == "__main__":
 
     time_add()
     time_matmul()
+    time_max()
     time_maximum()
     time_exp()
     time_negative()