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

common : auto-download dflash- and eagle3- HF sidecars (#25811)

Browse Source 
* 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:
Georgi Gerganov
2026-07-17 12:15:30 +03:00
committed by GitHub
parent 11fd0a6fb7
commit 635cdd5fcc
6 changed files with 91 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files
common/download.cpp
+23 -3
View File
@@ -620,6 +620,16 @@ static hf_cache::hf_file find_best_mtp(const hf_cache::hf_files & files,
return find_best_sibling(files, model, "mtp-");
}
static hf_cache::hf_file find_best_eagle3(const hf_cache::hf_files & files,
const std::string & model) {
return find_best_sibling(files, model, "eagle3-");
}
static hf_cache::hf_file find_best_dflash(const hf_cache::hf_files & files,
const std::string & model) {
return find_best_sibling(files, model, "dflash-");
}
static bool gguf_filename_is_model(const std::string & filepath) {
if (!string_ends_with(filepath, ".gguf")) {
return false;
@@ -632,7 +642,9 @@ static bool gguf_filename_is_model(const std::string & filepath) {
return filename.find("mmproj") == std::string::npos &&
filename.find("imatrix") == std::string::npos &&
filename.find("mtp-") == std::string::npos;
filename.find("mtp-") == std::string::npos &&
filename.find("eagle3-") == std::string::npos &&
filename.find("dflash-") == std::string::npos;
}
static hf_cache::hf_file find_best_model(const hf_cache::hf_files & files,
@@ -740,6 +752,12 @@ common_download_hf_plan common_download_get_hf_plan(const common_params_model &
if (opts.download_mtp) {
plan.mtp = find_best_mtp(all, primary.path);
}
if (opts.download_dflash) {
plan.dflash = find_best_dflash(all, primary.path);
}
if (opts.download_eagle3) {
plan.eagle3 = find_best_eagle3(all, primary.path);
}
return plan;
}
@@ -911,8 +929,10 @@ std::vector<common_cached_model_info> common_list_cached_models() {
for (const auto & f : files) {
auto split = get_gguf_split_info(f.path);
if (split.index != 1 || split.tag.empty() ||
split.prefix.find("mmproj") != std::string::npos ||
split.prefix.find("mtp-") != std::string::npos) {
split.prefix.find("mmproj") != std::string::npos ||
split.prefix.find("mtp-") != std::string::npos ||
split.prefix.find("eagle3-") != std::string::npos ||
split.prefix.find("dflash-") != std::string::npos) {
continue;
}
if (seen.insert(f.repo_id + ":" + split.tag).second) {