Lumpiasty/llama.cpp
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

common: apply CPU parameters across tools (#27026)

Browse Source
This commit is contained in:
Niklas Wenzel
2026-08-13 20:40:59 +02:00
committed by GitHub
parent bdffafa5df
commit a94d563ed8
3 changed files with 84 additions and 47 deletions
Download Patch File Download Diff File Expand all files Collapse all files
common/common.h
+24 -3
View File
@@ -929,9 +929,8 @@ using common_init_result_ptr = std::unique_ptr<common_init_result>;
common_init_result_ptr common_init_from_params(common_params & params, bool model_only = false);
struct llama_model_params common_model_params_to_llama ( common_params & params);
struct llama_context_params common_context_params_to_llama(const common_params & params);
struct ggml_threadpool_params ggml_threadpool_params_from_cpu_params(const common_cpu_params & params);
struct llama_model_params common_model_params_to_llama ( common_params & params);
struct llama_context_params common_context_params_to_llama(const common_params & params);
// clear LoRA adapters from context, then apply new list of adapters
void common_set_adapter_lora(struct llama_context * ctx, std::vector<common_adapter_lora_info> & lora);
@@ -942,6 +941,28 @@ std::string common_get_model_endpoint();
// for testing purposes
char * common_get_model_or_exit(int, char*[]);
//
// Threadpool utils
//
struct ggml_threadpool_params ggml_threadpool_params_from_cpu_params(const common_cpu_params & params);
struct common_threadpools {
common_threadpools() = default;
~common_threadpools();
common_threadpools(const common_threadpools &) = delete;
common_threadpools & operator=(const common_threadpools &) = delete;
void init(llama_context * ctx, const common_params & params);
private:
ggml_threadpool * threadpool = nullptr;
ggml_threadpool * threadpool_batch = nullptr;
decltype(ggml_threadpool_free) * free_fn = nullptr;
};
//
// Context utils
//