happyz
/
llama.cpp
mirror of https://github.com/ggerganov/llama.cpp.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Re-enable manual LoRA adapter free

This commit is contained in:
Pop Flamingo 2026-02-28 14:04:29 +01:00
parent 4720819d45
commit 1b60f08d67
4 changed files with 18 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
include/llama-cpp.h
View File

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

5
include/llama.h
View File

@ -647,9 +647,8 @@ 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
LLAMA_API DEPRECATED(void llama_adapter_lora_free(struct llama_adapter_lora * adapter),
"adapters are now freed together with the associated model");
// NOTE: loaded adapters that are not manually freed will be freed when the associated model is deleted
LLAMA_API void llama_adapter_lora_free(struct llama_adapter_lora * adapter);
// 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);

15
src/llama-adapter.cpp
View File

@ -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) {

4
src/llama-adapter.h
View File

@ -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);