diff --git a/ggml/src/ggml-cuda/argsort.cu b/ggml/src/ggml-cuda/argsort.cu
index 3722cf3ab2..b8003c48c5 100644
--- a/ggml/src/ggml-cuda/argsort.cu
+++ b/ggml/src/ggml-cuda/argsort.cu
@@ -49,28 +49,49 @@ static void argsort_f32_i32_cuda_cub(ggml_cuda_pool & pool,
     size_t temp_storage_bytes = 0;
 
     if (order == GGML_SORT_ORDER_ASC) {
-        DeviceSegmentedRadixSort::SortPairs(nullptr, temp_storage_bytes, temp_keys, temp_keys,  // keys (in-place)
-                                            temp_indices, dst,                                  // values (indices)
-                                            ncols * nrows, nrows,                            // num items, num segments
-                                            d_offsets, d_offsets + 1, 0, sizeof(float) * 8,  // all bits
-                                            stream);
+        if (nrows == 1) {
+            DeviceRadixSort::SortPairs(nullptr, temp_storage_bytes, temp_keys, temp_keys,  // keys (in-place)
+                                       temp_indices, dst,                                  // values (indices)
+                                       ncols, 0, sizeof(float) * 8, stream);
+        } else {
+            DeviceSegmentedSort::SortPairs(nullptr, temp_storage_bytes, temp_keys, temp_keys,  // keys (in-place)
+                                           temp_indices, dst,                                  // values (indices)
+                                           ncols * nrows, nrows,  // num items, num segments
+                                           d_offsets, d_offsets + 1, stream);
+        }
     } else {
-        DeviceSegmentedRadixSort::SortPairsDescending(nullptr, temp_storage_bytes, temp_keys, temp_keys, temp_indices,
-                                                      dst, ncols * nrows, nrows, d_offsets, d_offsets + 1, 0,
-                                                      sizeof(float) * 8, stream);
+        if (nrows == 1) {
+            DeviceRadixSort::SortPairsDescending(nullptr, temp_storage_bytes, temp_keys, temp_keys,  // keys (in-place)
+                                                 temp_indices, dst,                                  // values (indices)
+                                                 ncols, 0, sizeof(float) * 8, stream);
+        } else {
+            DeviceSegmentedSort::SortPairsDescending(nullptr, temp_storage_bytes, temp_keys, temp_keys, temp_indices,
+                                                     dst, ncols * nrows, nrows, d_offsets, d_offsets + 1, stream);
+        }
     }
 
     ggml_cuda_pool_alloc<uint8_t> temp_storage_alloc(pool, temp_storage_bytes);
     void *                        d_temp_storage = temp_storage_alloc.get();
 
     if (order == GGML_SORT_ORDER_ASC) {
-        DeviceSegmentedRadixSort::SortPairs(d_temp_storage, temp_storage_bytes, temp_keys, temp_keys, temp_indices, dst,
-                                            ncols * nrows, nrows, d_offsets, d_offsets + 1, 0, sizeof(float) * 8,
-                                            stream);
+        if (nrows == 1) {
+            DeviceRadixSort::SortPairs(d_temp_storage, temp_storage_bytes, temp_keys, temp_keys,  // keys (in-place)
+                                       temp_indices, dst,  // values (indices)
+                                       ncols, 0, sizeof(float) * 8, stream);
+        } else {
+            DeviceSegmentedSort::SortPairs(d_temp_storage, temp_storage_bytes, temp_keys, temp_keys, temp_indices, dst,
+                                           ncols * nrows, nrows, d_offsets, d_offsets + 1, stream);
+        }
     } else {
-        DeviceSegmentedRadixSort::SortPairsDescending(d_temp_storage, temp_storage_bytes, temp_keys, temp_keys,
-                                                      temp_indices, dst, ncols * nrows, nrows, d_offsets, d_offsets + 1,
-                                                      0, sizeof(float) * 8, stream);
+        if (nrows == 1) {
+            DeviceRadixSort::SortPairsDescending(d_temp_storage, temp_storage_bytes, temp_keys, temp_keys,  // keys (in-place)
+                                                 temp_indices, dst,                                  // values (indices)
+                                                 ncols, 0, sizeof(float) * 8, stream);
+        } else {
+            DeviceSegmentedSort::SortPairsDescending(d_temp_storage, temp_storage_bytes, temp_keys, temp_keys,
+                                                     temp_indices, dst, ncols * nrows, nrows, d_offsets, d_offsets + 1,
+                                                     stream);
+        }
     }
 }
 #endif  // GGML_CUDA_USE_CUB
diff --git a/tests/test-backend-ops.cpp b/tests/test-backend-ops.cpp
index 267bead8c4..fab8465934 100644
--- a/tests/test-backend-ops.cpp
+++ b/tests/test-backend-ops.cpp
@@ -7886,6 +7886,8 @@ static std::vector<std::unique_ptr<test_case>> make_test_cases_perf() {
     }
 
     test_cases.emplace_back(new test_argsort(GGML_TYPE_F32, {65000, 16, 1, 1}));
+    test_cases.emplace_back(new test_argsort(GGML_TYPE_F32, {200000, 1, 1, 1}));
+    test_cases.emplace_back(new test_argsort(GGML_TYPE_F32, {200000, 16, 1, 1}));
 
     return test_cases;
 }