diff --git a/ggml-cuda/argsort.cu b/ggml-cuda/argsort.cu
index 0e9ef4966..164144061 100644
--- a/ggml-cuda/argsort.cu
+++ b/ggml-cuda/argsort.cu
@@ -65,7 +65,7 @@ static int next_power_of_2(int x) {
     return n;
 }
 
-static void argsort_f32_i32_cuda(ggml_backend_cuda_context & ctx, const float * x, int * dst, const int ncols, const int nrows, ggml_sort_order order, cudaStream_t stream) {
+static void argsort_f32_i32_cuda(const float * x, int * dst, const int ncols, const int nrows, ggml_sort_order order, cudaStream_t stream) {
     // bitonic sort requires ncols to be power of 2
     const int ncols_pad = next_power_of_2(ncols);
 
@@ -99,5 +99,5 @@ void ggml_cuda_op_argsort(ggml_backend_cuda_context & ctx, ggml_tensor * dst) {
 
     enum ggml_sort_order order = (enum ggml_sort_order) dst->op_params[0];
 
-    argsort_f32_i32_cuda(ctx, src0_d, (int *)dst_d, ncols, nrows, order, stream);
+    argsort_f32_i32_cuda(src0_d, (int *)dst_d, ncols, nrows, order, stream);
 }