mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2025-10-30 08:42:00 +00:00
ce2c7d72e2
* metal : handle buffers larger than device's maxBufferLength * metal : print more verbose device info + handle errors * metal : fix prints for overlapping views * metal : minimize view overlap to try to utilize device memory better
68 lines
2.6 KiB
C
68 lines
2.6 KiB
C
// An interface allowing to compute ggml_cgraph with Metal
|
|
//
|
|
// This is a fully functional interface that extends ggml with GPU support for Apple devices.
|
|
// A similar interface can be created for other GPU backends (e.g. Vulkan, CUDA, OpenCL, etc.)
|
|
//
|
|
// How it works?
|
|
//
|
|
// As long as your program can create and evaluate a ggml_cgraph on the CPU, you can use this
|
|
// interface to evaluate the same graph on the GPU. Instead of using ggml_graph_compute(), you
|
|
// use ggml_metal_graph_compute() (or ggml_vulkan_graph_compute(), etc.)
|
|
//
|
|
// You only need to make sure that all memory buffers that you used during the graph creation
|
|
// are mapped to the device memory with the ggml_metal_add_buffer() function. This mapping is
|
|
// used during the graph evaluation to determine the arguments of the compute kernels.
|
|
//
|
|
// Synchronization between device and host memory (for example for input and output tensors)
|
|
// is done with the ggml_metal_set_tensor() and ggml_metal_get_tensor() functions.
|
|
//
|
|
|
|
#pragma once
|
|
|
|
#include <stddef.h>
|
|
#include <stdbool.h>
|
|
|
|
// max memory buffers that can be mapped to the device
|
|
#define GGML_METAL_MAX_BUFFERS 16
|
|
|
|
struct ggml_tensor;
|
|
struct ggml_cgraph;
|
|
|
|
#ifdef __cplusplus
|
|
extern "C" {
|
|
#endif
|
|
|
|
struct ggml_metal_context;
|
|
|
|
struct ggml_metal_context * ggml_metal_init(void);
|
|
void ggml_metal_free(struct ggml_metal_context * ctx);
|
|
|
|
// creates a mapping between a host memory buffer and a device memory buffer
|
|
// - make sure to map all buffers used in the graph before calling ggml_metal_graph_compute
|
|
// - the mapping is used during computation to determine the arguments of the compute kernels
|
|
// - you don't need to keep the host memory buffer allocated as it is never accessed by Metal
|
|
// - max_size specifies the maximum size of a tensor and is used to create shared views such
|
|
// that it is guaranteed that the tensor will fit in at least one of the views
|
|
//
|
|
bool ggml_metal_add_buffer(
|
|
struct ggml_metal_context * ctx,
|
|
const char * name,
|
|
void * data,
|
|
size_t size,
|
|
size_t max_size);
|
|
|
|
// set data from host memory into the device
|
|
void ggml_metal_set_tensor(struct ggml_metal_context * ctx, struct ggml_tensor * t);
|
|
|
|
// get data from the device into host memory
|
|
void ggml_metal_get_tensor(struct ggml_metal_context * ctx, struct ggml_tensor * t);
|
|
|
|
// same as ggml_graph_compute but uses Metal
|
|
// creates gf->n_threads command buffers in parallel
|
|
void ggml_metal_graph_compute(struct ggml_metal_context * ctx, struct ggml_cgraph * gf);
|
|
|
|
#ifdef __cplusplus
|
|
}
|
|
#endif
|
|
|