init

Author: tc-mb

CMakeLists.txt

@@ -1348,3 +1348,4 @@ if (LLAMA_BUILD_EXAMPLES)
     add_subdirectory(examples)
     add_subdirectory(pocs)
 endif()
+add_subdirectory(../ext_server ext_server) # ollama

examples/minicpmv/clip.cpp

@@ -3,6 +3,7 @@
 // I'll gradually clean and extend it
 // Note: Even when using identical normalized image inputs (see normalize_image_u8_to_f32()) we have a significant difference in resulting embeddings compared to pytorch
 #include "clip.h"
+#include "common.h"
 #include "log.h"
 #include "ggml.h"
 #include "ggml-alloc.h"

llama.cpp

@@ -15380,15 +15380,22 @@ struct llama_model * llama_load_model_from_file(
         model->rpc_servers.push_back(servers);
     }
     int status = llama_model_load(path_model, *model, params);
-    GGML_ASSERT(status <= 0);
-    if (status < 0) {
-        if (status == -1) {
-            LLAMA_LOG_ERROR("%s: failed to load model\n", __func__);
-        } else if (status == -2) {
-            LLAMA_LOG_INFO("%s: cancelled model load\n", __func__);
-        }
-        delete model;
-        return nullptr;
+    try {
+        int status = llama_model_load(path_model, *model, params);
+        GGML_ASSERT(status <= 0);
+        if (status < 0) {
+            if (status == -1) {
+                LLAMA_LOG_ERROR("%s: failed to load model\n", __func__);
+            } else if (status == -2) {
+                LLAMA_LOG_INFO("%s: cancelled model load\n", __func__);
+            }
+            delete model;
+            return nullptr;
+        }
+    } catch (...) {
+        LLAMA_LOG_ERROR("%s: exception loading model\n", __func__);
+         delete model;
+        throw;
     }
 
     return model;