llama-cpp-turboquant/common/hf-cache.h
Adrien Gallouët 8c7957ca33
common : add standard Hugging Face cache support (#20775)
* common : add standard Hugging Face cache support

- Use HF API to find all files
- Migrate all manifests to hugging face cache at startup

Signed-off-by: Adrien Gallouët <angt@huggingface.co>

* Check with the quant tag

Signed-off-by: Adrien Gallouët <angt@huggingface.co>

* Cleanup

Signed-off-by: Adrien Gallouët <angt@huggingface.co>

* Improve error handling and report API errors

Signed-off-by: Adrien Gallouët <angt@huggingface.co>

* Restore common_cached_model_info and align mmproj filtering

Signed-off-by: Adrien Gallouët <angt@huggingface.co>

* Prefer main when getting cached ref

Signed-off-by: Adrien Gallouët <angt@huggingface.co>

* Use cached files when HF API fails

Signed-off-by: Adrien Gallouët <angt@huggingface.co>

* Use final_path..

Signed-off-by: Adrien Gallouët <angt@huggingface.co>

* Check all inputs

Signed-off-by: Adrien Gallouët <angt@huggingface.co>

---------

Signed-off-by: Adrien Gallouët <angt@huggingface.co>
2026-03-24 07:30:33 +01:00

35 lines
754 B
C++

#pragma once
#include <string>
#include <vector>
// Ref: https://huggingface.co/docs/hub/local-cache.md
namespace hf_cache {
struct hf_file {
std::string path;
std::string url;
std::string local_path;
std::string final_path;
std::string oid;
std::string repo_id;
};
using hf_files = std::vector<hf_file>;
// Get files from HF API
hf_files get_repo_files(
const std::string & repo_id,
const std::string & token
);
hf_files get_cached_files(const std::string & repo_id = {});
// Create snapshot path (link or move/copy) and return it
std::string finalize_file(const hf_file & file);
// TODO: Remove later
void migrate_old_cache_to_hf_cache(const std::string & token, bool offline = false);
} // namespace hf_cache