mirror of
https://github.com/ggerganov/llama.cpp.git
synced 2024-11-11 21:39:52 +00:00
ecb217db4f
* mtl : export the LLaMA computation graph
* ci : disable temporary
* mtl : adapt the MNIST example as starter
* mtl : no need for mtl-export tool, add cli arg for main instead
* mtl : export just a small part of the graph for now to make it easier
* mtl : move MSL code into separate file for easy editing
* mtl : initial get_rows_q4_0 kernel
* mtl : confirmed get_rows_q4_0 is working correctly
* mtl : add rms_norm kernel + confirm working
* mtl : add mul kernel + confirm working
* mtl : initial mul_mat Q4 kernel (wrong results)
* mtl : mul_mat fixes (still wrong)
* mtl : another mul_mat Q4 (still does not work)
* mtl : working mul_mat q4
* ggml : fix handling of "view" ops in ggml_graph_import()
* mtl : add rope kernel
* mtl : add reshape and transpose handling
* ggml : store offset as opt arg for ggml_view_xd() operators
* mtl : add cpy kernel + handle view ops
* mtl : confirm f16 x f32 attention mul mat
* mtl : add scale kernel
* mtl : add diag_mask_inf kernel
* mtl : fix soft_max kernel
* ggml : update ggml_nbytes() to handle non-contiguous tensors
* mtl : verify V tensor contents
* mtl : add f32 -> f32 cpy kernel
* mtl : add silu kernel
* mtl : add non-broadcast mul kernel
* mtl : full GPU inference of the computation graph
* mtl : optimize rms_norm and soft_max kernels
* mtl : add f16 mat x f32 vec multiplication kernel
* mtl : fix bug in f16 x f32 mul mat + speed-up computation
* mtl : faster mul_mat_q4_0_f32 kernel
* mtl : fix kernel signature + roll inner loop
* mtl : more threads for rms_norm + better timing
* mtl : remove printfs from inner loop
* mtl : simplify implementation
* mtl : add save/load vocab to ggml file
* mtl : plug Metal inference into llama.cpp (very quick-n-dirty)
* mtl : make it work with main example
Lots of hacks but at least now it generates text
* mtl : preparing for merge
* mtl : clean-up ggml mtl interface + suport scratch / inplace
* mtl : remove temp / debug code
* metal : final refactoring and simplification
* Revert "ci : disable temporary"
This reverts commit 98c267fc77.
* metal : add comments
* metal : clean-up stuff, fix typos
* readme : add Metal instructions
* readme : add example for main
64 lines
2.3 KiB
C
64 lines
2.3 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
|
|
//
|
|
bool ggml_metal_add_buffer(
|
|
struct ggml_metal_context * ctx,
|
|
const char * name,
|
|
void * data,
|
|
size_t 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
|
|
void ggml_metal_graph_compute(struct ggml_metal_context * ctx, struct ggml_cgraph * gf);
|
|
|
|
#ifdef __cplusplus
|
|
}
|
|
#endif
|
|
|