whisper.cpp/ggml-vulkan.h
0cc4m 9c399689ec
Vulkan Improvements (llama/5835)
* Improve dequant shaders, add fast q4_0 dequant

* Optimize dmmv non-kquants for GCN

Remove unnecessary SPIR-V shader duplication

* Fix q4_0 dequant dispatch sizes

Fix backend free bug

* Optimize dequant shaders for q4_1, q5_0, q5_1 and q8_0

* Add unary and binary op shader templates

* Fix Vulkan check results

* Enable non-contiguous support for simple ops

* Add argsort

Basic q4_0 mmq shader and unit test

* Speed up q4_0 dequant code, enable mmq for q4_0

* Rework matmul pipeline selection

* Add soft_max alibi support

* Add q4_1, q5_0, q5_1 and q8_0 dequant mat mat mul shaders

* Add environment variable GGML_VK_FORCE_MAX_ALLOCATION_SIZE to limit max buffer size

Rename GGML_VULKAN_DISABLE_F16 to GGML_VK_DISABLE_F16 for consistency
2024-03-08 11:38:33 +02:00

41 lines
1.6 KiB
C

#pragma once
#include "ggml.h"
#include "ggml-backend.h"
#ifdef __cplusplus
extern "C" {
#endif
#define GGML_VK_NAME "Vulkan"
#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);
GGML_API GGML_CALL bool ggml_backend_is_vk(ggml_backend_t backend);
GGML_API GGML_CALL int ggml_backend_vk_get_device_count(void);
GGML_API GGML_CALL void ggml_backend_vk_get_device_description(int device, char * description, size_t description_size);
GGML_API GGML_CALL void ggml_backend_vk_get_device_memory(int device, size_t * free, size_t * total);
GGML_API GGML_CALL ggml_backend_buffer_type_t ggml_backend_vk_buffer_type(size_t dev_num);
// pinned host buffer for use with the CPU backend for faster copies between CPU and GPU
GGML_API GGML_CALL ggml_backend_buffer_type_t ggml_backend_vk_host_buffer_type(void);
#ifdef __cplusplus
}
#endif