llamacppctl/tests
dschlueter 218c3fc791 feat(docker): support a multimodal projector via --mmproj
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>
2026-07-10 16:24:47 +02:00
..
conftest.py Initial commit: llamacppctl – llama.cpp Docker server control CLI 2026-07-06 16:36:27 +02:00
test_actions.py feat(docker): support a multimodal projector via --mmproj 2026-07-10 16:24:47 +02:00
test_build_archive.py test: cover build_archive and add it to the ruff scope 2026-07-07 11:20:57 +02:00
test_cli.py test: close coverage gaps + opt-in integration smoke 2026-07-06 17:08:10 +02:00
test_config.py feat(docker): support a multimodal projector via --mmproj 2026-07-10 16:24:47 +02:00
test_docker_ops.py feat(docker): support a multimodal projector via --mmproj 2026-07-10 16:24:47 +02:00
test_http_ops.py chore(ci): add ruff and mypy, wire them into CI 2026-07-07 10:29:07 +02:00
test_lock_ops.py Initial commit: llamacppctl – llama.cpp Docker server control CLI 2026-07-06 16:36:27 +02:00
test_prompt_files.py Initial commit: llamacppctl – llama.cpp Docker server control CLI 2026-07-06 16:36:27 +02:00
test_prompt_sources.py Initial commit: llamacppctl – llama.cpp Docker server control CLI 2026-07-06 16:36:27 +02:00
test_prompt_urls.py test: close coverage gaps + opt-in integration smoke 2026-07-06 17:08:10 +02:00