llama : re-enable manual LoRA adapter free (#19983)

* Re-enable manual LoRA adapter free

* Remove stale "all adapters must be loaded before context creation" stale comments

common/common.cpp

@@ -1067,7 +1067,7 @@ common_init_result::common_init_result(common_params & params) :
 
     const llama_vocab * vocab = llama_model_get_vocab(model);
 
-    // load and optionally apply lora adapters (must be loaded before context creation)
+    // load and optionally apply lora adapters
     for (auto & la : params.lora_adapters) {
         llama_adapter_lora_ptr lora;
         lora.reset(llama_adapter_lora_init(model, la.path.c_str()));

include/llama-cpp.h

@@ -21,9 +21,7 @@ struct llama_sampler_deleter {
 };
 
 struct llama_adapter_lora_deleter {
-    void operator()(llama_adapter_lora *) {
+    void operator()(llama_adapter_lora * adapter) { llama_adapter_lora_free(adapter); }
-        // llama_adapter_lora_free is deprecated
-    }
 };
 
 typedef std::unique_ptr<llama_model, llama_model_deleter> llama_model_ptr;

include/llama.h

@@ -636,7 +636,6 @@ extern "C" {
 
     // Load a LoRA adapter from file
     // The adapter is valid as long as the associated model is not freed
-    // All adapters must be loaded before context creation
     LLAMA_API struct llama_adapter_lora * llama_adapter_lora_init(
             struct llama_model * model,
             const char * path_lora);
@@ -660,9 +659,8 @@ extern "C" {
     LLAMA_API int32_t llama_adapter_meta_val_str_by_index(const struct llama_adapter_lora * adapter, int32_t i, char * buf, size_t buf_size);
 
     // Manually free a LoRA adapter
-    // NOTE: loaded adapters will be free when the associated model is deleted
+    // NOTE: loaded adapters that are not manually freed will be freed when the associated model is deleted
-    LLAMA_API DEPRECATED(void llama_adapter_lora_free(struct llama_adapter_lora * adapter),
+    LLAMA_API void llama_adapter_lora_free(struct llama_adapter_lora * adapter);
-            "adapters are now freed together with the associated model");
 
     // Get the invocation tokens if the current lora is an alora
     LLAMA_API uint64_t            llama_adapter_get_alora_n_invocation_tokens(const struct llama_adapter_lora * adapter);

src/llama-adapter.cpp

@@ -418,7 +418,7 @@ static void llama_adapter_lora_init_impl(llama_model & model, const char * path_
 }
 
 llama_adapter_lora * llama_adapter_lora_init(llama_model * model, const char * path_lora) {
-    llama_adapter_lora * adapter = new llama_adapter_lora();
+    llama_adapter_lora * adapter = new llama_adapter_lora(model);
 
     try {
         llama_adapter_lora_init_impl(*model, path_lora, *adapter);
@@ -471,8 +471,17 @@ int32_t llama_adapter_meta_val_str_by_index(const llama_adapter_lora * adapter,
     return snprintf(buf, buf_size, "%s", it->second.c_str());
 }
 
-void llama_adapter_lora_free(llama_adapter_lora *) {
+void llama_adapter_lora_free(llama_adapter_lora * adapter) {
-    // deprecated: adapters are freed by llama_model's destructor
+    if (adapter == nullptr) {
+        return;
+    }
+
+    if (adapter->model != nullptr) {
+        adapter->model->loras.erase(adapter);
+        adapter->model = nullptr;
+    }
+
+    delete adapter;
 }
 
 uint64_t llama_adapter_get_alora_n_invocation_tokens(const struct llama_adapter_lora * adapter) {

src/llama-adapter.h

@@ -61,6 +61,8 @@ struct llama_adapter_lora_weight {
 };
 
 struct llama_adapter_lora {
+    llama_model * model = nullptr;
+
     // map tensor name to lora_a_b
     std::unordered_map<std::string, llama_adapter_lora_weight> ab_map;
 
@@ -75,7 +77,7 @@ struct llama_adapter_lora {
     // activated lora (aLoRA)
     std::vector<llama_token> alora_invocation_tokens;
 
-    llama_adapter_lora() = default;
+    explicit llama_adapter_lora(llama_model * model) : model(model) {}
     ~llama_adapter_lora() = default;
 
     llama_adapter_lora_weight * get_weight(ggml_tensor * w);