CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-12 10:47:01 +00:00
Code Issues Packages Projects Releases Wiki Activity

arg: add --cache-list argument to list cached models (#17073)

Browse Source 
* arg: add --cache-list argument to list cached models

* new manifest naming format

* improve naming

* Update common/arg.cpp

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit is contained in:
Xuan-Son Nguyen
2025-11-08 21:54:14 +01:00
committed by GitHub
parent 333f2595a3
commit aa3b7a90b4
5 changed files with 117 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

22
common/download.h
View File

@@ -8,16 +8,23 @@ struct common_params_model;
// download functionalities
//
struct common_cached_model_info {
std::string manifest_path;
std::string user;
std::string model;
std::string tag;
size_t size = 0; // GGUF size in bytes
std::string to_string() const {
return user + "/" + model + ":" + tag;
}
};
struct common_hf_file_res {
std::string repo; // repo name with ":tag" removed
std::string ggufFile;
std::string mmprojFile;
};
// resolve and download model from Docker registry
// return local path to downloaded model file
std::string common_docker_resolve_model(const std::string & docker);
/**
* Allow getting the HF file from the HF repo with tag (like ollama), for example:
* - bartowski/Llama-3.2-3B-Instruct-GGUF:q4
@@ -39,3 +46,10 @@ bool common_download_model(
const common_params_model & model,
const std::string & bearer_token,
bool offline);
// returns list of cached models
std::vector<common_cached_model_info> common_list_cached_models();
// resolve and download model from Docker registry
// return local path to downloaded model file
std::string common_docker_resolve_model(const std::string & docker);