CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-30 08:42:00 +00:00
Code Issues Packages Projects Releases Wiki Activity

llava : expose as a shared library for downstream projects (#3613)

Browse Source 
* wip llava python bindings compatibility

* add external llava API

* add base64 in-prompt image support

* wip refactor image loading

* refactor image load out of llava init

* cleanup

* further cleanup; move llava-cli into its own file and rename

* move base64.hpp into common/

* collapse clip and llava libraries

* move llava into its own subdir

* wip

* fix bug where base64 string was not removed from the prompt

* get libllava to output in the right place

* expose llava methods in libllama.dylib

* cleanup memory usage around clip_image_*

* cleanup and refactor *again*

* update headerdoc

* build with cmake, not tested (WIP)

* Editorconfig

* Editorconfig

* Build with make

* Build with make

* Fix cyclical depts on Windows

* attempt to fix build on Windows

* attempt to fix build on Windows

* Upd TODOs

* attempt to fix build on Windows+CUDA

* Revert changes in cmake

* Fix according to review comments

* Support building as a shared library

* address review comments

---------

Co-authored-by: M. Yusuf Sarıgöz <yusufsarigoz@gmail.com>
Co-authored-by: Jared Van Bortel <jared@nomic.ai>
This commit is contained in:
Damian Stewart
2023-11-06 22:36:23 +01:00
committed by GitHub
parent 2833a6f63c
commit 381efbf480
13 changed files with 1022 additions and 354 deletions
Download Patch File Download Diff File Expand all files Collapse all files

41
examples/llava/clip.h
View File

@@ -1,7 +1,22 @@
#ifndef CLIP_H
#define CLIP_H
#include "ggml.h"
#include <stddef.h>
#include <stdint.h>
#ifdef LLAMA_SHARED
# if defined(_WIN32) && !defined(__MINGW32__)
# ifdef LLAMA_BUILD
# define CLIP_API __declspec(dllexport)
# else
# define CLIP_API __declspec(dllimport)
# endif
# else
# define CLIP_API __attribute__ ((visibility ("default")))
# endif
#else
# define CLIP_API
#endif
struct clip_ctx;
@@ -20,19 +35,20 @@ struct clip_vision_hparams {
float eps;
};
struct clip_ctx * clip_model_load(const char * fname, const int verbosity);
/** load mmproj model */
CLIP_API struct clip_ctx * clip_model_load(const char * fname, const int verbosity);
/** free mmproj model */
CLIP_API void clip_free(struct clip_ctx * ctx);
void clip_free(struct clip_ctx * ctx);
size_t clip_embd_nbytes(struct clip_ctx * ctx);
int clip_n_patches(struct clip_ctx * ctx);
int clip_n_mmproj_embd(struct clip_ctx * ctx);
size_t clip_embd_nbytes(const struct clip_ctx * ctx);
int clip_n_patches(const struct clip_ctx * ctx);
int clip_n_mmproj_embd(const struct clip_ctx * ctx);
// RGB uint8 image
struct clip_image_u8 {
int nx;
int ny;
uint8_t * data;
uint8_t * data = NULL;
size_t size;
};
@@ -41,7 +57,7 @@ struct clip_image_u8 {
struct clip_image_f32 {
int nx;
int ny;
float * data;
float * data = NULL;
size_t size;
};
@@ -57,7 +73,12 @@ struct clip_image_f32_batch {
struct clip_image_u8 * make_clip_image_u8();
struct clip_image_f32 * make_clip_image_f32();
bool clip_image_load_from_file(const char * fname, struct clip_image_u8 * img);
CLIP_API void clip_image_u8_free(clip_image_u8 * img);
CLIP_API void clip_image_f32_free(clip_image_f32 * img);
CLIP_API bool clip_image_load_from_file(const char * fname, struct clip_image_u8 * img);
/** interpret bytes as an image file with length bytes_length, and use the result to populate img */
CLIP_API bool clip_image_load_from_bytes(const unsigned char * bytes, size_t bytes_length, struct clip_image_u8 * img);
bool clip_image_preprocess(const struct clip_ctx * ctx, const struct clip_image_u8 * img, struct clip_image_f32 * res, const bool pad2square);
bool clip_image_encode(const struct clip_ctx * ctx, const int n_threads, struct clip_image_f32 * img, float * vec);