diff --git a/megatron/fused_kernels/type_shim.h b/megatron/fused_kernels/type_shim.h
index 6b1c8927d..c8dbd1f10 100644
--- a/megatron/fused_kernels/type_shim.h
+++ b/megatron/fused_kernels/type_shim.h
@@ -277,7 +277,7 @@ reduce_block_into_lanes(T* x,
             final = x[tid] + x[tid + 32];
         else
             final = val;
-            // __SYNCWARP();
+        // __SYNCWARP();
 
 #pragma unroll
         for (int i = 16; i >= lanes; i >>= 1)
@@ -321,7 +321,7 @@ reduce_block_into_lanes_max_op(T* x,
             final = fmaxf(fabsf(x[tid]), fabsf(x[tid + 32]));
         else
             final = val;
-            // __SYNCWARP();
+        // __SYNCWARP();
 
 #pragma unroll
         for (int i = 16; i >= lanes; i >>= 1)