common : auto-download dflash- and eagle3- HF sidecars (#25811)
* common: auto-download dflash- and eagle3- HF sidecars Mirror the existing mtp- sidecar logic to support auto-discovery and download of DFlash (dflash-) and Eagle3 (eagle3-) speculative decoding sidecars from Hugging Face repos. Changes: - Add --dflash and --eagle3 CLI flags to trigger sidecar download - Add find_best_dflash() and find_best_eagle3() using find_best_sibling - Exclude dflash- and eagle3- filenames from primary model selection - Filter dflash- and eagle3- from cached model listings - Wire download tasks that set speculative.draft.mparams as fallback Assisted-by: pi:llama.cpp/Qwen3.6-27B * docs : regen
This commit is contained in:
+6
-2
@@ -55,8 +55,10 @@ struct common_download_opts {
|
||||
std::string bearer_token;
|
||||
common_header_list headers;
|
||||
bool offline = false;
|
||||
bool download_mmproj = false;
|
||||
bool download_mtp = false;
|
||||
bool download_mmproj = false;
|
||||
bool download_mtp = false;
|
||||
bool download_eagle3 = false;
|
||||
bool download_dflash = false;
|
||||
common_download_callback * callback = nullptr;
|
||||
};
|
||||
|
||||
@@ -106,6 +108,8 @@ struct common_download_hf_plan {
|
||||
hf_cache::hf_files model_files;
|
||||
hf_cache::hf_file mmproj;
|
||||
hf_cache::hf_file mtp;
|
||||
hf_cache::hf_file eagle3;
|
||||
hf_cache::hf_file dflash;
|
||||
hf_cache::hf_file preset; // if set, only this file is downloaded
|
||||
};
|
||||
common_download_hf_plan common_download_get_hf_plan(const common_params_model & model, const common_download_opts & opts);
|
||||
|
||||
Reference in New Issue
Block a user