From ba0c7c70ab5b15f1f2be7fb0dfbe0366dda30d6c Mon Sep 17 00:00:00 2001 From: 0cc4m Date: Fri, 29 Mar 2024 17:29:21 +0100 Subject: Vulkan k-quant mmq and ggml-backend offload functionality (#6155) * Fix Vulkan no kv offload incoherence * Add k-quant mul mat mat shaders * Rework working buffer allocation, reduces vram use noticeably Clean up cpu assist code, replaced with ggml-backend offload function * Default to all dedicated GPUs * Add fallback for integrated GPUs if no dedicated GPUs are found * Add debug info which device is allocating memory * Fix Intel dequant issue Fix validation issue * Fix Vulkan GGML_OP_GET_ROWS implementation * Clean up merge artifacts * Remove Vulkan warning --- ggml-vulkan.h | 11 ----------- 1 file changed, 11 deletions(-) (limited to 'ggml-vulkan.h') diff --git a/ggml-vulkan.h b/ggml-vulkan.h index e4317c3e..af661c2d 100644 --- a/ggml-vulkan.h +++ b/ggml-vulkan.h @@ -11,17 +11,6 @@ extern "C" { #define GGML_VK_MAX_DEVICES 16 GGML_API void ggml_vk_instance_init(void); -GGML_API void ggml_vk_init_cpu_assist(void); - -GGML_API void ggml_vk_preallocate_buffers_graph_cpu_assist(struct ggml_tensor * node); -GGML_API void ggml_vk_preallocate_buffers_cpu_assist(void); -GGML_API void ggml_vk_build_graph_cpu_assist(struct ggml_tensor * node, bool last_node); -GGML_API bool ggml_vk_compute_forward_cpu_assist(struct ggml_compute_params * params, struct ggml_tensor * tensor); -#ifdef GGML_VULKAN_CHECK_RESULTS -void ggml_vk_check_results_1_cpu_assist(struct ggml_compute_params * params, struct ggml_tensor * tensor); -#endif -GGML_API void ggml_vk_graph_cleanup_cpu_assist(void); -GGML_API void ggml_vk_free_cpu_assist(void); // backend API GGML_API GGML_CALL ggml_backend_t ggml_backend_vk_init(size_t dev_num); -- cgit v1.2.3