Skip to content

fix(runtime): finalize HF model download (create snapshot symlink) — fixes model-not-found on every binary #47

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
SnowCheetos merged 1 commit into from
Jul 8, 2026
Merged

fix(runtime): finalize HF model download (create snapshot symlink) — fixes model-not-found on every binary #47

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
9 changes: 7 additions & 2 deletions crates/llama-sys/src/autocommit_common_bridge.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -12,6 +12,7 @@
#include "arg.h"
#include "common.h"
#include "download.h"
#include "hf-cache.h"
#include "log.h"
#include "sampling.h"

Expand Down Expand Up @@ -154,8 +155,12 @@ static std::string resolve_hf_model(autocommit_common_config & cfg) {
common_download_task task(plan.primary, opts);
common_download_run_tasks({ task });

// After download, the final cached path is available
model.path = plan.primary.final_path.empty() ? plan.primary.local_path : plan.primary.final_path;
// finalize_file creates the HF-cache snapshot symlink
// (snapshots/<rev>/<file> -> ../../blobs/<sha>) and returns the path to use:
// the snapshot symlink, or the blob path itself if symlink creation fails.
// Without it the blob downloads but the resolved final_path dangles. Mirrors
// how llama.cpp's own common/arg.cpp finalizes downloaded models.
model.path = hf_cache::finalize_file(plan.primary);
return model.path;
}

Expand Down
Loading