dschlueter
218c3fc791
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>
219 lines
6.8 KiB
Python
219 lines
6.8 KiB
Python
import sys
|
|
from pathlib import Path
|
|
from unittest.mock import patch, MagicMock
|
|
|
|
sys.path.insert(0, str(Path(__file__).resolve().parents[1] / "src"))
|
|
|
|
from llamacppctl.docker_ops import ( # noqa: E402
|
|
build_run_command,
|
|
container_exists,
|
|
container_running,
|
|
docker_available,
|
|
format_command_for_display,
|
|
inspect_container,
|
|
)
|
|
from llamacppctl.schema import ServerConfig # noqa: E402
|
|
|
|
|
|
def make_cfg(**overrides) -> ServerConfig:
|
|
base = dict(
|
|
image="ghcr.io/ggml-org/llama.cpp:server-cuda",
|
|
hf_home=Path("/srv/models"),
|
|
model_path="qwen3/default.gguf",
|
|
container_name="test_llm",
|
|
host_port=8001,
|
|
container_port=8000,
|
|
model_alias="default_llm",
|
|
gpu_device="0",
|
|
restart_policy="unless-stopped",
|
|
ctx_size=262144,
|
|
n_predict=16384,
|
|
temp=0.65,
|
|
top_p=0.80,
|
|
top_k=20,
|
|
min_p=0.01,
|
|
repeat_penalty=1.05,
|
|
main_gpu=0,
|
|
ngl=999,
|
|
batch_size=1024,
|
|
ubatch_size=512,
|
|
parallel=1,
|
|
cache_type_k="q4_0",
|
|
cache_type_v="q4_0",
|
|
reasoning="on",
|
|
jinja=True,
|
|
fa=True,
|
|
kv_unified=True,
|
|
cont_batching=True,
|
|
no_context_shift=True,
|
|
host="0.0.0.0",
|
|
health_endpoint="/health",
|
|
models_endpoint="/v1/models",
|
|
chat_endpoint="/v1/chat/completions",
|
|
timeout=300,
|
|
poll_interval=2.0,
|
|
lock_file=Path("/tmp/llamacppctl.test_llm.lock"),
|
|
)
|
|
base.update(overrides)
|
|
return ServerConfig(**base)
|
|
|
|
|
|
def test_docker_available_true():
|
|
with patch("subprocess.run") as mock_run:
|
|
mock_run.return_value = MagicMock(returncode=0)
|
|
assert docker_available() is True
|
|
|
|
|
|
def test_docker_available_false_when_missing():
|
|
with patch("subprocess.run", side_effect=FileNotFoundError()):
|
|
assert docker_available() is False
|
|
|
|
|
|
def test_container_exists_true():
|
|
with patch("llamacppctl.docker_ops._run") as mock_run:
|
|
mock_run.return_value = MagicMock(stdout="test_llm\nother\n")
|
|
assert container_exists("test_llm") is True
|
|
|
|
|
|
def test_container_exists_false():
|
|
with patch("llamacppctl.docker_ops._run") as mock_run:
|
|
mock_run.return_value = MagicMock(stdout="other\n")
|
|
assert container_exists("test_llm") is False
|
|
|
|
|
|
def test_container_running_true():
|
|
with patch("llamacppctl.docker_ops._run") as mock_run:
|
|
mock_run.return_value = MagicMock(stdout="test_llm\n")
|
|
assert container_running("test_llm") is True
|
|
|
|
|
|
def test_inspect_container_missing():
|
|
with patch("llamacppctl.docker_ops.container_exists", return_value=False):
|
|
info = inspect_container("ghost")
|
|
assert info.status == "missing"
|
|
assert info.health == "none"
|
|
|
|
|
|
def test_inspect_container_running():
|
|
fake_json = (
|
|
'[{"State": {"Status": "running", "Health": {"Status": "healthy"}}}]'
|
|
)
|
|
with patch("llamacppctl.docker_ops.container_exists", return_value=True), patch(
|
|
"llamacppctl.docker_ops._run"
|
|
) as mock_run:
|
|
mock_run.return_value = MagicMock(stdout=fake_json)
|
|
info = inspect_container("test_llm")
|
|
assert info.status == "running"
|
|
assert info.health == "healthy"
|
|
|
|
|
|
def test_build_run_command_contains_key_flags():
|
|
cfg = make_cfg()
|
|
cmd = build_run_command(cfg)
|
|
assert cmd[0:2] == ["docker", "run"]
|
|
assert "--gpus" in cmd
|
|
assert "device=0" in cmd
|
|
assert "--name" in cmd
|
|
assert "test_llm" in cmd
|
|
assert "-p" in cmd
|
|
# loopback-only by default (expose=False)
|
|
assert "127.0.0.1:8001:8000" in cmd
|
|
assert "--jinja" in cmd
|
|
assert "--reasoning" in cmd
|
|
assert "on" in cmd
|
|
assert "--no-context-shift" in cmd
|
|
assert "--kv-unified" in cmd
|
|
assert "--cont-batching" in cmd
|
|
|
|
|
|
def test_build_run_command_overrides_healthcheck_to_configured_port():
|
|
cfg = make_cfg()
|
|
cmd = build_run_command(cfg)
|
|
assert "--health-cmd" in cmd
|
|
# healthcheck must target the configured container_port (8000), not the
|
|
# image default (8080), and hit the configured health endpoint.
|
|
assert "curl -f http://localhost:8000/health || exit 1" in cmd
|
|
assert "--health-start-period" in cmd
|
|
|
|
|
|
def test_build_run_command_expose_binds_all_interfaces():
|
|
cfg = make_cfg(expose=True)
|
|
cmd = build_run_command(cfg)
|
|
assert "8001:8000" in cmd
|
|
assert "127.0.0.1:8001:8000" not in cmd
|
|
|
|
|
|
def test_build_run_command_api_key_passed_to_server():
|
|
cfg = make_cfg(api_key="secret123")
|
|
cmd = build_run_command(cfg)
|
|
assert "--api-key" in cmd
|
|
assert "secret123" in cmd
|
|
|
|
|
|
def test_build_run_command_no_api_key_by_default():
|
|
cfg = make_cfg()
|
|
assert "--api-key" not in build_run_command(cfg)
|
|
|
|
|
|
def test_build_run_command_respects_disabled_flags():
|
|
cfg = make_cfg(jinja=False, kv_unified=False, cont_batching=False, no_context_shift=False, fa=False)
|
|
cmd = build_run_command(cfg)
|
|
assert "--jinja" not in cmd
|
|
assert "--kv-unified" not in cmd
|
|
assert "--cont-batching" not in cmd
|
|
assert "--no-context-shift" not in cmd
|
|
|
|
|
|
def test_build_run_command_absolute_model_path():
|
|
cfg = make_cfg(model_path="/abs/path/model.gguf")
|
|
cmd = build_run_command(cfg)
|
|
idx = cmd.index("-m")
|
|
assert cmd[idx + 1] == "/abs/path/model.gguf"
|
|
|
|
|
|
def test_build_run_command_relative_model_path():
|
|
cfg = make_cfg(model_path="qwen3/default.gguf")
|
|
cmd = build_run_command(cfg)
|
|
idx = cmd.index("-m")
|
|
assert cmd[idx + 1] == "/hf_home/qwen3/default.gguf"
|
|
|
|
|
|
def test_build_run_command_no_mmproj_by_default():
|
|
cmd = build_run_command(make_cfg())
|
|
assert "--mmproj" not in cmd
|
|
assert "--no-mmproj-offload" not in cmd
|
|
|
|
|
|
def test_build_run_command_mmproj_relative_path_resolves_under_hf_home():
|
|
cfg = make_cfg(mmproj="qwen3/mmproj.gguf")
|
|
cmd = build_run_command(cfg)
|
|
idx = cmd.index("--mmproj")
|
|
assert cmd[idx + 1] == "/hf_home/qwen3/mmproj.gguf"
|
|
# offload is llama.cpp's default, so the opt-out flag must stay absent
|
|
assert "--no-mmproj-offload" not in cmd
|
|
|
|
|
|
def test_build_run_command_mmproj_absolute_path_passed_through():
|
|
cfg = make_cfg(mmproj="/abs/mmproj.gguf")
|
|
cmd = build_run_command(cfg)
|
|
idx = cmd.index("--mmproj")
|
|
assert cmd[idx + 1] == "/abs/mmproj.gguf"
|
|
|
|
|
|
def test_build_run_command_mmproj_offload_disabled():
|
|
cfg = make_cfg(mmproj="qwen3/mmproj.gguf", mmproj_offload=False)
|
|
cmd = build_run_command(cfg)
|
|
assert "--no-mmproj-offload" in cmd
|
|
|
|
|
|
def test_build_run_command_no_mmproj_offload_needs_mmproj():
|
|
# Without a projector the offload opt-out is meaningless and must not leak
|
|
# into the command line (llama.cpp would reject it).
|
|
cfg = make_cfg(mmproj="", mmproj_offload=False)
|
|
assert "--no-mmproj-offload" not in build_run_command(cfg)
|
|
|
|
|
|
def test_format_command_for_display_quotes_properly():
|
|
cmd = ["docker", "run", "--name", "has space"]
|
|
out = format_command_for_display(cmd)
|
|
assert "'has space'" in out
|