add test target

Author: ngxson

examples/llava/clip.h

@@ -78,10 +78,10 @@ CLIP_API int clip_uhd_num_image_embeds_col(struct clip_ctx * ctx_clip);
 CLIP_API void clip_add_load_image_size(struct clip_ctx * ctx_clip, struct clip_image_size * load_image_size);
 CLIP_API struct clip_image_size * clip_get_load_image_size(struct clip_ctx * ctx_clip);
 
-CLIP_API struct clip_image_size      * clip_image_size_init();
-CLIP_API struct clip_image_u8        * clip_image_u8_init ();
-CLIP_API struct clip_image_f32       * clip_image_f32_init();
-CLIP_API struct clip_image_f32_batch * clip_image_f32_batch_init(); // only used by libllava
+CLIP_API struct clip_image_size      * clip_image_size_init(void);
+CLIP_API struct clip_image_u8        * clip_image_u8_init (void);
+CLIP_API struct clip_image_f32       * clip_image_f32_init(void);
+CLIP_API struct clip_image_f32_batch * clip_image_f32_batch_init(void); // only used by libllava
 
 // nx, ny are the output image dimensions
 CLIP_API unsigned char * clip_image_u8_get_data(struct clip_image_u8 * img, uint32_t * nx, uint32_t * ny);

examples/llava/mtmd.cpp

@@ -888,3 +888,36 @@ llama_pos mtmd_image_tokens_get_n_pos(const mtmd_image_tokens * image_tokens) {
     }
     return image_tokens->n_tokens();
 }
+
+// test function
+
+mtmd_input_chunks * mtmd_test_create_input_chunks() {
+    mtmd_input_chunks * chunks = mtmd_input_chunks_init();
+    if (!chunks) {
+        return nullptr;
+    }
+
+    // create a text chunk
+    std::vector<llama_token> tokens_text = { 1, 2, 3, 4, 5 };
+    mtmd_input_chunk chunk_text{
+        MTMD_INPUT_CHUNK_TYPE_TEXT,
+        std::move(tokens_text),
+        {},
+    };
+    chunks->entries.emplace_back(std::move(chunk_text));
+
+    // create an image chunk
+    mtmd_image_tokens_ptr image_tokens(new mtmd_image_tokens);
+    image_tokens->nx = 4;
+    image_tokens->ny = 4;
+    image_tokens->batch_f32.entries.resize(16);
+    image_tokens->id = "image_1";
+    mtmd_input_chunk chunk_image{
+        MTMD_INPUT_CHUNK_TYPE_IMAGE,
+        {},
+        std::move(image_tokens),
+    };
+    chunks->entries.emplace_back(std::move(chunk_image));
+
+    return chunks;
+}

examples/llava/mtmd.h

@@ -73,7 +73,7 @@ struct mtmd_context_params {
     const char * image_marker;
 };
 
-MTMD_API mtmd_context_params mtmd_context_params_default();
+MTMD_API struct mtmd_context_params mtmd_context_params_default(void);
 
 // initialize the mtmd context
 // return nullptr on failure
@@ -111,7 +111,7 @@ MTMD_API void         mtmd_bitmap_set_id  (mtmd_bitmap * bitmap, const char * id
 //
 // this is simply a list of mtmd_input_chunk
 // the elements can only be populated via mtmd_tokenize()
-MTMD_API mtmd_input_chunks * mtmd_input_chunks_init();
+MTMD_API mtmd_input_chunks * mtmd_input_chunks_init(void);
 MTMD_API size_t              mtmd_input_chunks_size(mtmd_input_chunks * chunks);
 MTMD_API mtmd_input_chunk *  mtmd_input_chunks_get (mtmd_input_chunks * chunks, size_t idx);
 MTMD_API void                mtmd_input_chunks_free(mtmd_input_chunks * chunks);
@@ -228,6 +228,9 @@ MTMD_API int32_t mtmd_helper_eval_chunk_single(mtmd_context * ctx,
 
 /////////////////////////////////////////
 
+// test function, to be used in test-mtmd-c-api.c
+MTMD_API mtmd_input_chunks * mtmd_test_create_input_chunks(void);
+
 #ifdef __cplusplus
 } // extern "C"
 #endif

tests/CMakeLists.txt

@@ -162,6 +162,10 @@ if (NOT GGML_BACKEND_DL)
     llama_build_and_test(test-rope.cpp)
 endif()
 
+# libmtmd
+set(LLAMA_TEST_NAME test-mtmd-c-api)
+llama_build_and_test(test-mtmd-c-api.c)
+target_link_libraries(${LLAMA_TEST_NAME} PRIVATE mtmd)
 
 # dummy executable - not installed
 get_filename_component(TEST_TARGET test-c.c NAME_WE)

tests/test-mtmd-c-api.c

@@ -0,0 +1,61 @@
+#include <stdio.h>
+#include <assert.h>
+
+#define MTMD_TEST
+#include "mtmd.h"
+
+int main(void) {
+    printf("\n\nTesting libmtmd C API...\n");
+    printf("--------\n\n");
+
+    struct mtmd_context_params params = mtmd_context_params_default();
+    printf("Default image marker: %s\n", params.image_marker);
+
+    mtmd_input_chunks * chunks = mtmd_test_create_input_chunks();
+
+    if (!chunks) {
+        fprintf(stderr, "Failed to create input chunks\n");
+        return 1;
+    }
+
+    size_t n_chunks = mtmd_input_chunks_size(chunks);
+    printf("Number of chunks: %zu\n", n_chunks);
+    assert(n_chunks > 0);
+
+    for (size_t i = 0; i < n_chunks; i++) {
+        mtmd_input_chunk * chunk = mtmd_input_chunks_get(chunks, i);
+        assert(chunk != NULL);
+        enum mtmd_input_chunk_type type = mtmd_input_chunk_get_type(chunk);
+        printf("Chunk %zu type: %d\n", i, type);
+
+        if (type == MTMD_INPUT_CHUNK_TYPE_TEXT) {
+            size_t n_tokens;
+            const llama_token * tokens = mtmd_input_chunk_get_tokens_text(chunk, &n_tokens);
+            printf("    Text chunk with %zu tokens\n", n_tokens);
+            assert(tokens != NULL);
+            assert(n_tokens > 0);
+            for (size_t j = 0; j < n_tokens; j++) {
+                assert(tokens[j] >= 0);
+                printf("    > Token %zu: %d\n", j, tokens[j]);
+            }
+
+        } else if (type == MTMD_INPUT_CHUNK_TYPE_IMAGE) {
+            const mtmd_image_tokens * image_tokens = mtmd_input_chunk_get_tokens_image(chunk);
+            size_t n_tokens = mtmd_image_tokens_get_n_tokens(image_tokens);
+            size_t nx = mtmd_image_tokens_get_nx(image_tokens);
+            size_t ny = mtmd_image_tokens_get_ny(image_tokens);
+            const char * id = mtmd_image_tokens_get_id(image_tokens);
+            assert(n_tokens > 0);
+            assert(nx > 0);
+            assert(ny > 0);
+            assert(id != NULL);
+            printf("    Image chunk with %zu tokens\n", n_tokens);
+            printf("    Image size: %zu x %zu\n", nx, ny);
+            printf("    Image ID: %s\n", id);
+        }
+    }
+
+    printf("\n\nDONE: test libmtmd C API...\n");
+
+    return 0;
+}