sleepy/llama.cpp
1
0
Fork 0
Code Issues 9 Pull Requests Actions 103 Packages Projects Releases Wiki Activity

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

Browse Source 
* Re-enable manual LoRA adapter free

* Remove stale "all adapters must be loaded before context creation" stale comments
This commit is contained in:
Pop Flamingo
2026-03-18 11:03:26 +01:00
committed by GitHub
parent f4049ad735
commit 312cf03328
5 changed files with 19 additions and 12 deletions
Download Patch File Download Diff File Expand all files Collapse all files
include/llama-cpp.h
+1 -3
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;
include/llama.h
+2 -4
View File
@@ -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
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);