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

* 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>

1 files changed, 50 insertions, 0 deletions

diff --git a/examples/llava/llava.h b/examples/llava/llava.h
new file mode 100644
index 00000000..e08ce788
--- /dev/null
+++ b/examples/llava/llava.h
@@ -0,0 +1,50 @@
+#ifndef LLAVA_H
+#define LLAVA_H
+
+#include "ggml.h"
+
+
+#ifdef LLAMA_SHARED
+#    if defined(_WIN32) && !defined(__MINGW32__)
+#        ifdef LLAMA_BUILD
+#            define LLAVA_API __declspec(dllexport)
+#        else
+#            define LLAVA_API __declspec(dllimport)
+#        endif
+#    else
+#        define LLAVA_API __attribute__ ((visibility ("default")))
+#    endif
+#else
+#    define LLAVA_API
+#endif
+
+struct clip_ctx;
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+struct llava_image_embed {
+    float * embed;
+    int n_image_pos;
+};
+
+/** sanity check for clip <-> llava embed size match */
+LLAVA_API bool llava_validate_embed_size(const llama_context * ctx_llama, const clip_ctx * ctx_clip);
+
+/** build an image embed from image file bytes */
+LLAVA_API struct llava_image_embed * llava_image_embed_make_with_bytes(struct clip_ctx * ctx_clip, int n_threads, const unsigned char * image_bytes, int image_bytes_length);
+/** build an image embed from a path to an image filename */
+LLAVA_API struct llava_image_embed * llava_image_embed_make_with_filename(struct clip_ctx * ctx_clip, int n_threads, const char * image_path);
+LLAVA_API void llava_image_embed_free(struct llava_image_embed * embed);
+/** free an embedding made with llava_image_embed_make_* */
+
+/** write the image represented by embed into the llama context with batch size n_batch, starting at context pos n_past. on completion, n_past points to the next position in the context after the image embed. */
+LLAVA_API bool llava_eval_image_embed(struct llama_context * ctx_llama, const struct llava_image_embed * embed, int n_batch, int * n_past);
+
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif