zhangyiss/mlx
1
0
Fork 0
mirror of https://github.com/ml-explore/mlx.git synced 2025-12-16 01:49:05 +08:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity

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

Browse Source 
* 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.
This commit is contained in:
jhavukainen
2025-07-09 11:26:27 -07:00
committed by GitHub
parent fb4e8b896b
commit 8b9a3f3cea
7 changed files with 131 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

14
mlx/backend/cpu/reduce.cpp
View File

@@ -325,7 +325,15 @@ struct MaxReduce {
};
template <int N, typename T>
T operator()(simd::Simd<T, N> x) {
std::enable_if_t<std::is_integral_v<T>, T> operator()(simd::Simd<T, N> x) {
return simd::max(x);
};
template <int N, typename T>
std::enable_if_t<!std::is_integral_v<T>, T> operator()(simd::Simd<T, N> x) {
if (simd::any(x != x)) {
return static_cast<T>(NAN);
}
return simd::max(x);
};
};
@@ -527,10 +535,10 @@ void Reduce::eval_cpu(const std::vector<array>& inputs, array& out) {
reduce_dispatch_min_max<uint64_t>(in, out, reduce_type_, axes_);
break;
case int8:
reduce_dispatch_min_max<uint8_t>(in, out, reduce_type_, axes_);
reduce_dispatch_min_max<int8_t>(in, out, reduce_type_, axes_);
break;
case int16:
reduce_dispatch_min_max<uint16_t>(in, out, reduce_type_, axes_);
reduce_dispatch_min_max<int16_t>(in, out, reduce_type_, axes_);
break;
case int32:
reduce_dispatch_min_max<int32_t>(in, out, reduce_type_, axes_);