Vision-capable GGUFs need a separate projector (mmproj) that maps image embeddings into the text model's space. Add `mmproj` and `mmproj_offload` as config keys and CLI overrides, and pass them through to llama-server. The projector path resolves under hf_home exactly like model_path, so it is covered by the existing read-only mount. validate_model_path() now also checks the projector, which means --change rejects a missing one *before* it removes the running container. --no-mmproj-offload is suppressed when no projector is configured, since llama.cpp rejects the flag on its own. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> |
||
|---|---|---|
| .. | ||
| conftest.py | ||
| test_actions.py | ||
| test_build_archive.py | ||
| test_cli.py | ||
| test_config.py | ||
| test_docker_ops.py | ||
| test_http_ops.py | ||
| test_lock_ops.py | ||
| test_prompt_files.py | ||
| test_prompt_sources.py | ||
| test_prompt_urls.py | ||