diff --git a/CMakeLists.txt b/CMakeLists.txt
index 7177846ce..2ccbfb694 100644
--- a/CMakeLists.txt
+++ b/CMakeLists.txt
@@ -24,7 +24,7 @@ option(MLX_METAL_JIT "Use JIT compilation for Metal kernels" OFF)
 option(BUILD_SHARED_LIBS "Build mlx as a shared library" OFF)
 
 if(NOT MLX_VERSION)
-  set(MLX_VERSION 0.17.0)
+  set(MLX_VERSION 0.17.1)
 endif()
 
 # --------------------- Processor tests -------------------------
diff --git a/mlx/backend/metal/reduce.cpp b/mlx/backend/metal/reduce.cpp
index 2c8f18430..95f6e2eff 100644
--- a/mlx/backend/metal/reduce.cpp
+++ b/mlx/backend/metal/reduce.cpp
@@ -308,7 +308,11 @@ void all_reduce_dispatch(
     compute_encoder.dispatchThreads(grid_dims, group_dims);
 
     // 2nd pass
-    compute_encoder->setComputePipelineState(kernel);
+    std::ostringstream kname_2nd_pass;
+    kname_2nd_pass << "all_reduce_" << op_name << type_to_name(intermediate);
+    auto kernel_2nd_pass =
+        get_reduce_kernel(d, kname_2nd_pass.str(), op_name, intermediate, out);
+    compute_encoder->setComputePipelineState(kernel_2nd_pass);
     size_t intermediate_size = n_rows;
     grid_dims = MTL::Size(threadgroup_2nd_pass, 1, 1);
     group_dims = MTL::Size(threadgroup_2nd_pass, 1, 1);
diff --git a/python/tests/test_reduce.py b/python/tests/test_reduce.py
index f47a357dd..c59e7f490 100644
--- a/python/tests/test_reduce.py
+++ b/python/tests/test_reduce.py
@@ -124,6 +124,13 @@ def test_edge_case(self):
         z = np.array(x).sum((0, 2, 3))
         self.assertTrue(np.all(z == y))
 
+    def test_sum_bool(self):
+        x = np.random.uniform(0, 1, size=(10, 10, 10)) > 0.5
+        y = mx.array(x)
+        npsum = x.sum().item()
+        mxsum = y.sum().item()
+        self.assertEqual(npsum, mxsum)
+
 
 if __name__ == "__main__":
     unittest.main(failfast=True)
diff --git a/setup.py b/setup.py
index 3a2fbac3b..410ae262e 100644
--- a/setup.py
+++ b/setup.py
@@ -163,7 +163,7 @@ def run(self) -> None:
 
     setup(
         name="mlx",
-        version=get_version("0.17.0"),
+        version=get_version("0.17.1"),
         author="MLX Contributors",
         author_email="mlx@group.apple.com",
         description="A framework for machine learning on Apple silicon.",