LLM inference in C/C++
C++ ggml
vulkan : Fix undeclared identifiers when -DGGML_VULKAN_RUN_TESTS=ON (#29912)
Ed Addarioebe18bee5a1b
diff --git a/ggml/src/ggml-vulkan/ggml-vulkan-common.h b/ggml/src/ggml-vulkan/ggml-vulkan-common.hindex 125e7608a3..a642c55165 100644--- a/ggml/src/ggml-vulkan/ggml-vulkan-common.h+++ b/ggml/src/ggml-vulkan/ggml-vulkan-common.h@@ -233,6 +233,18 @@ ggml_backend_reg_t ggml_backend_vk_reg();// debugint64_t ggml_vk_get_op_batch_size(const ggml_tensor * op);+#ifdef GGML_VULKAN_RUN_TESTS+template <typename X_TYPE, typename Y_TYPE>+void ggml_vk_test_matmul(ggml_backend_vk_context * ctx, size_t m, size_t n, size_t k, size_t batch, size_t num_it, int split_k, int shader_size);+void ggml_vk_test_dequant(ggml_backend_vk_context * ctx, size_t ne, ggml_type quant);+void ggml_vk_test_dequant_matmul(ggml_backend_vk_context * ctx, size_t m, size_t n, size_t k, size_t batch, size_t num_it, size_t split_k, size_t shader_size, ggml_type quant, bool mmq = false);+#endif+#ifdef GGML_VULKAN_CHECK_RESULTS+extern size_t vk_skip_checks;+extern size_t vk_output_tensor;+void ggml_vk_check_results_0(ggml_backend_vk_context * ctx, ggml_cgraph * cgraph, int tensor_idx);+void ggml_vk_check_results_1(ggml_backend_vk_context * ctx, ggml_cgraph * cgraph, int tensor_idx);+#endif// ggml-vulkan.cpp (residual)bool ggml_vk_lightning_indexer_k_type_supported(ggml_type type);diff --git a/ggml/src/ggml-vulkan/ggml-vulkan-debug.cpp b/ggml/src/ggml-vulkan/ggml-vulkan-debug.cppindex 15abd54681..8d8fe65922 100644--- a/ggml/src/ggml-vulkan/ggml-vulkan-debug.cpp+++ b/ggml/src/ggml-vulkan/ggml-vulkan-debug.cpp@@ -47,12 +47,10 @@ void vk_memory_logger::log_deallocation(vk_buffer_ref buf_ref) {}#ifdef GGML_VULKAN_CHECK_RESULTS-static size_t vk_skip_checks;-static size_t vk_output_tensor;+size_t vk_skip_checks;+size_t vk_output_tensor;static void ggml_vk_print_tensor(const ggml_tensor * tensor, const char * name);-static void ggml_vk_check_results_0(ggml_backend_vk_context * ctx, ggml_cgraph * cgraph, int tensor_idx);-static void ggml_vk_check_results_1(ggml_backend_vk_context * ctx, ggml_cgraph * cgraph, int tensor_idx);#endif#ifdef GGML_VULKAN_RUN_TESTS@@ -90,7 +88,7 @@ static void ggml_vk_print_matrix_area(const void * data, ggml_type type, int ne0}template <typename X_TYPE, typename Y_TYPE>-static void ggml_vk_test_matmul(ggml_backend_vk_context * ctx, size_t m, size_t n, size_t k, size_t batch, size_t num_it, int split_k, int shader_size) {+void ggml_vk_test_matmul(ggml_backend_vk_context * ctx, size_t m, size_t n, size_t k, size_t batch, size_t num_it, int split_k, int shader_size) {VK_LOG_DEBUG("ggml_vk_test_matmul(" << m << ", " << n << ", " << k << ", " << batch << ", " << num_it << ", " << split_k << ", " << shader_size << ")");const size_t x_ne = m * k * batch;const size_t y_ne = k * n * batch;@@ -297,6 +295,8 @@ static void ggml_vk_test_matmul(ggml_backend_vk_context * ctx, size_t m, size_tfree(d);}+template void ggml_vk_test_matmul<ggml_fp16_t, float>(ggml_backend_vk_context * ctx, size_t m, size_t n, size_t k, size_t batch, size_t num_it, int split_k, int shader_size);+static void ggml_vk_print_tensor_area(const ggml_tensor * tensor, int i0, int i1, int i2, int i3) {if (tensor->type != GGML_TYPE_F32 && tensor->type != GGML_TYPE_F16) {return;@@ -348,7 +348,7 @@ static void ggml_vk_dequantize_data(const void * from, float * to, size_t ne, ggdequant_fn(from, to, ne);}-static void ggml_vk_test_dequant(ggml_backend_vk_context * ctx, size_t ne, ggml_type quant) {+void ggml_vk_test_dequant(ggml_backend_vk_context * ctx, size_t ne, ggml_type quant) {VK_LOG_DEBUG("ggml_vk_test_dequant(" << ne << ")");const size_t x_sz = sizeof(float) * ne;const size_t x_sz_f16 = sizeof(ggml_fp16_t) * ne;@@ -540,7 +540,7 @@ static void ggml_vk_test_dequant(ggml_backend_vk_context * ctx, size_t ne, ggml_// free(qx_res);// }-static void ggml_vk_test_dequant_matmul(ggml_backend_vk_context * ctx, size_t m, size_t n, size_t k, size_t batch, size_t num_it, size_t split_k, size_t shader_size, ggml_type quant, bool mmq = false) {+void ggml_vk_test_dequant_matmul(ggml_backend_vk_context * ctx, size_t m, size_t n, size_t k, size_t batch, size_t num_it, size_t split_k, size_t shader_size, ggml_type quant, bool mmq) {VK_LOG_DEBUG("ggml_vk_test_dequant_matmul(" << m << ", " << n << ", " << k << ", " << batch << ", " << num_it << ", " << split_k << ", " << ggml_type_name(quant) << ")");const size_t x_ne = m * k * batch;const size_t y_ne = k * n * batch;@@ -871,7 +871,7 @@ void * comp_result;size_t comp_size;size_t comp_nb[GGML_MAX_DIMS];size_t check_counter = 0;-static void ggml_vk_check_results_0(ggml_backend_vk_context * ctx, ggml_cgraph * cgraph, int tensor_idx) {+void ggml_vk_check_results_0(ggml_backend_vk_context * ctx, ggml_cgraph * cgraph, int tensor_idx) {ggml_tensor * tensor = cgraph->nodes[tensor_idx + ctx->num_additional_fused_ops];if (tensor->op == GGML_OP_TRANSPOSE || tensor->op == GGML_OP_SET_ROWS) {return;@@ -1374,7 +1374,7 @@ static void ggml_vk_check_results_0(ggml_backend_vk_context * ctx, ggml_cgraph *VK_LOG_DEBUG("END ggml_vk_check_results_0(" << tensor->name << ")");}-static void ggml_vk_check_results_1(ggml_backend_vk_context * ctx, ggml_cgraph * cgraph, int tensor_idx) {+void ggml_vk_check_results_1(ggml_backend_vk_context * ctx, ggml_cgraph * cgraph, int tensor_idx) {ggml_tensor * tensor = cgraph->nodes[tensor_idx + ctx->num_additional_fused_ops];if (tensor->op == GGML_OP_TRANSPOSE || tensor->op == GGML_OP_SET_ROWS) {return;