server : support llava 1.6 (#5553)

* server: init working 1.6

* move clip_image to header

* remove commented code

* remove c++ style from header

* remove todo

* expose llava_image_embed_make_with_clip_img

* fix zig build

3 files changed, 6 insertions, 34 deletions

diff --git a/examples/llava/llava.cpp b/examples/llava/llava.cpp
index 4cb65a07..1a1cf7c7 100644
--- a/examples/llava/llava.cpp
+++ b/examples/llava/llava.cpp
@@ -311,7 +311,7 @@ bool llava_validate_embed_size(const llama_context * ctx_llama, const clip_ctx *
     return true;
 }
 
-static bool llava_image_embed_make_with_clip_img(clip_ctx * ctx_clip, int n_threads, const clip_image_u8 * img, float ** image_embd_out, int * n_img_pos_out) {
+bool llava_image_embed_make_with_clip_img(clip_ctx * ctx_clip, int n_threads, const clip_image_u8 * img, float ** image_embd_out, int * n_img_pos_out) {
     float * image_embd = (float *)malloc(clip_embd_nbytes(ctx_clip)*6); // TODO: base on gridsize/llava model
     if (!image_embd) {
         fprintf(stderr, "Unable to allocate memory for image embeddings\n");
diff --git a/examples/llava/llava.h b/examples/llava/llava.h
index 9e9466a5..2d40f3f1 100644
--- a/examples/llava/llava.h
+++ b/examples/llava/llava.h
@@ -31,6 +31,8 @@ struct llava_image_embed {
 /** 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);
 
+LLAVA_API bool llava_image_embed_make_with_clip_img(clip_ctx * ctx_clip, int n_threads, const clip_image_u8 * img, float ** image_embd_out, int * n_img_pos_out);
+
 /** 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 */
diff --git a/examples/server/server.cpp b/examples/server/server.cpp
index c7821eca..eb01729f 100644
--- a/examples/server/server.cpp
+++ b/examples/server/server.cpp
@@ -5,6 +5,7 @@
 #include "oai.hpp"
 
 #include "../llava/clip.h"
+#include "../llava/llava.h"
 
 #include "stb_image.h"
 
@@ -997,43 +998,12 @@ struct llama_server_context
             {
                 continue;
             }
-            clip_image_f32_batch img_res_v;
-            img_res_v.size = 0;
-            img_res_v.data = nullptr;
-            if (!clip_image_preprocess(clp_ctx, img.img_data, img_res_v))
-            {
-                LOG_TEE("Error processing the given image");
-                clip_free(clp_ctx);
-                clip_image_f32_batch_free(img_res_v);
-                return false;
-            }
-            if (img_res_v.size == 0)
-            {
-                LOG_TEE("Error processing the given image");
-                return false;
-            }
-
-            // note: assumes only one image was returned by clip_image_preprocess
-            clip_image_f32 * img_res = img_res_v.data;
 
-            img.image_tokens = clip_n_patches(clp_ctx);
-            img.image_embedding = (float *)malloc(clip_embd_nbytes(clp_ctx));
-            if (!img.image_embedding)
-            {
-                LOG_TEE("Unable to allocate memory for image embeddings\n");
-                clip_image_f32_batch_free(img_res_v);
-                clip_free(clp_ctx);
-                return false;
-            }
-            LOG_TEE("slot %i - encoding image [id: %i]\n", slot.id, img.id);
-            if (!clip_image_encode(clp_ctx, params.n_threads, img_res, img.image_embedding))
-            {
-                LOG_TEE("Unable to encode image\n");
-                clip_image_f32_batch_free(img_res_v);
+            if (!llava_image_embed_make_with_clip_img(clp_ctx, params.n_threads, img.img_data, &img.image_embedding, &img.image_tokens)) {
+                LOG_TEE("Error processing the given image");
                 return false;
             }
 
-            clip_image_f32_batch_free(img_res_v);
 
             img.request_encode_image = false;
         }