-
Stefy Lanza (nextime / spora ) authored
A gguf model's assigned/loaded key is its file path, but /v1/models advertises it — and clients address it — by the filename without the .gguf suffix (the automatic alias). engine_for_assigned / engine_for_model / _key_matches_path compared short names verbatim, so the automatic alias never matched the .gguf key and routing fell through (404 / wrong engine). Normalize both sides via _short_stem so the automatic alias resolves to the owning engine with no manual alias. Co-Authored-By:Claude Opus 4.8 <noreply@anthropic.com>
2eda7574
| Name |
Last commit
|
Last update |
|---|---|---|
| .. | ||
| __init__.py | ||
| app.py | ||
| assignment.py | ||
| engine_supervisor.py | ||
| gpu_detect.py | ||
| registry.py | ||
| router.py |