talk-llama : sync llama.cpp

Author: ggerganov

examples/talk-llama/llama-adapter.cpp

@@ -294,7 +294,7 @@ static void llama_adapter_lora_init_impl(llama_model & model, const char * path_
     }
 
     // get extra buffer types of the CPU
-    // TODO: a more general solution for non-CPU extra buft should be imlpemented in the future
+    // TODO: a more general solution for non-CPU extra buft should be implemented in the future
     //       ref: https://github.com/ggml-org/llama.cpp/pull/12593#pullrequestreview-2718659948
     std::vector<ggml_backend_buffer_type_t> buft_extra;
     {
@@ -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 *) {
-    // deprecated: adapters are freed by llama_model's destructor
+void llama_adapter_lora_free(llama_adapter_lora * adapter) {
+    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) {

examples/talk-llama/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);