diff --git a/ggml-opencl.cpp b/ggml-opencl.cpp
index e0c6f089f..8ac4686b3 100644
--- a/ggml-opencl.cpp
+++ b/ggml-opencl.cpp
@@ -993,11 +993,11 @@ static void ggml_cl_mul_mat_q_f32(const ggml_tensor * src0, const ggml_tensor *
     cl_kernel* dmmv = ggml_get_dequantize_mul_mat_vec_cl(type);
     GGML_ASSERT(to_fp32_cl != nullptr);
 
+    size_t ev_idx = 0;
+    std::vector<cl_event> events;
+
     for (int64_t i03 = 0; i03 < ne03; i03++) {
         for (int64_t i02 = 0; i02 < ne02; i02++) {
-            size_t ev_idx = 0;
-            std::vector<cl_event> events;
-
             // copy src0 to device if necessary
             if (src0->backend == GGML_BACKEND_CPU) {
                 events.emplace_back();
@@ -1061,6 +1061,9 @@ static void ggml_cl_mul_mat_q_f32(const ggml_tensor * src0, const ggml_tensor *
             for (auto *event : events) {
                 clReleaseEvent(event);
             }
+
+            ev_idx = 0;
+            events.clear();
         }
     }
 
diff --git a/ggml-opencl.h b/ggml-opencl.h
index ff419c306..20e9cd37c 100644
--- a/ggml-opencl.h
+++ b/ggml-opencl.h
@@ -17,7 +17,7 @@ void * ggml_cl_host_malloc(size_t size);
 void   ggml_cl_host_free(void * ptr);
 
 void ggml_cl_transform_tensor(struct ggml_tensor * tensor);
-void ggml_cl_load_data(const char * fname, struct ggml_tensor * tensor, const size_t offset);
+void ggml_cl_load_data(const char * fname, struct ggml_tensor * tensor, size_t offset);
 
 #ifdef  __cplusplus
 }
diff --git a/llama.cpp b/llama.cpp
index 51c4168db..3df41e7f6 100644
--- a/llama.cpp
+++ b/llama.cpp
@@ -1012,8 +1012,10 @@ static void llama_model_load_internal(
 
 #if defined(GGML_USE_CUBLAS)
 #define LLAMA_BACKEND_OFFLOAD GGML_BACKEND_CUDA
+    fprintf(stderr, "%s: using CUDA for GPU acceleration\n", __func__);
 #elif defined(GGML_USE_CLBLAST)
 #define LLAMA_BACKEND_OFFLOAD GGML_BACKEND_CL
+    fprintf(stderr, "%s: using OpenCL for GPU acceleration\n", __func__);
 #else
 #define LLAMA_BACKEND_OFFLOAD GGML_BACKEND_CPU
 #endif
@@ -1095,22 +1097,14 @@ static void llama_model_load_internal(
         fprintf(stderr, "%s: mem required  = %7.2f MB (+ %7.2f MB per state)\n", __func__,
                 mem_required / 1024.0 / 1024.0, mem_required_state / 1024.0 / 1024.0);
 
-#if defined(GGML_USE_CUBLAS)
         const int n_gpu = std::min(n_gpu_layers, int(hparams.n_layer));
 
-        fprintf(stderr, "%s: [cublas] offloading %d layers to GPU\n", __func__, n_gpu);
+#if defined(GGML_USE_CUBLAS) || defined(GGML_USE_CLBLAST)
+        fprintf(stderr, "%s: offloading %d layers to GPU\n", __func__, n_gpu);
         if (n_gpu_layers > (int) hparams.n_layer) {
-            fprintf(stderr, "%s: [cublas] offloading output layer to GPU\n", __func__);
+            fprintf(stderr, "%s: offloading output layer to GPU\n", __func__);
         }
-        fprintf(stderr, "%s: [cublas] total VRAM used: %zu MB\n", __func__, vram_total / 1024 / 1024);
-#elif defined(GGML_USE_CLBLAST)
-        const int n_gpu = std::min(n_gpu_layers, int(hparams.n_layer));
-
-        fprintf(stderr, "%s: [opencl] offloading %d layers to GPU\n", __func__, n_gpu);
-        if (n_gpu_layers > (int) hparams.n_layer) {
-            fprintf(stderr, "%s: [opencl] offloading output layer to GPU\n", __func__);
-        }
-        fprintf(stderr, "%s: [opencl] total VRAM used: %zu MB\n", __func__, vram_total / 1024 / 1024);
+        fprintf(stderr, "%s: total VRAM used: %zu MB\n", __func__, vram_total / 1024 / 1024);
 #else
         (void) n_gpu_layers;
 #endif