[Config Refactor] Support Recursive Merging for Engine Args (#3009)
Signed-off-by: Alex Brooks <albrooks@redhat.com> Signed-off-by: Hongsheng Liu <liuhongsheng4@huawei.com> Co-authored-by: SYLAR <125541396+lishunyang12@users.noreply.github.com> Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
This commit is contained in:
2 files changed
+240
-185
No files matched your search
+196
-158
@@ -4,27 +4,40 @@
|
||||
Unit tests for StageConfigFactory and related classes.
|
||||
"""
|
||||
|
||||
import importlib
|
||||
import inspect
|
||||
import warnings
|
||||
from dataclasses import dataclass
|
||||
from dataclasses import dataclass, fields
|
||||
from pathlib import Path
|
||||
from unittest.mock import patch
|
||||
|
||||
import pytest
|
||||
|
||||
from tests.helpers.stage_config import get_deploy_config_path
|
||||
from vllm_omni.config.stage_config import (
|
||||
_PIPELINE_REGISTRY,
|
||||
DeployConfig,
|
||||
ModelPipeline,
|
||||
PipelineConfig,
|
||||
StageConfig,
|
||||
StageConfigFactory,
|
||||
StageDeployConfig,
|
||||
StageExecutionType,
|
||||
StagePipelineConfig,
|
||||
StageType,
|
||||
_apply_platform_overrides,
|
||||
_deep_merge_stage,
|
||||
_resolve_scheduler,
|
||||
build_stage_runtime_overrides,
|
||||
deploy_override_field_names,
|
||||
load_deploy_config,
|
||||
merge_pipeline_deploy,
|
||||
register_pipeline,
|
||||
strip_parent_engine_args,
|
||||
)
|
||||
from vllm_omni.engine.arg_utils import SHARED_FIELDS, internal_blacklist_keys
|
||||
from vllm_omni.engine.arg_utils import SHARED_FIELDS, EngineArgs, internal_blacklist_keys
|
||||
|
||||
pytestmark = [pytest.mark.core_model, pytest.mark.cpu]
|
||||
|
||||
|
||||
class TestStageType:
|
||||
@@ -99,8 +112,6 @@ class TestStageConfig:
|
||||
|
||||
def test_to_omegaconf_with_runtime_overrides(self):
|
||||
"""Test that runtime overrides are applied to OmegaConf output."""
|
||||
import warnings
|
||||
|
||||
config = StageConfig(
|
||||
stage_id=0,
|
||||
model_stage="thinker",
|
||||
@@ -123,8 +134,6 @@ class TestStageConfig:
|
||||
|
||||
def test_to_omegaconf_max_batch_size_deprecation(self):
|
||||
"""Test that runtime.max_batch_size emits a FutureWarning."""
|
||||
import warnings
|
||||
|
||||
config = StageConfig(
|
||||
stage_id=0,
|
||||
model_stage="thinker",
|
||||
@@ -149,7 +158,6 @@ class TestStageConfig:
|
||||
|
||||
def test_to_omegaconf_omits_none_deploy_overrides_for_engine_args(self):
|
||||
"""None deploy overrides must fall through to EngineArgs defaults."""
|
||||
from vllm_omni.config.stage_config import deploy_override_field_names
|
||||
|
||||
config = StageConfig(
|
||||
stage_id=0,
|
||||
@@ -370,11 +378,7 @@ class TestStageResolutionHelpers:
|
||||
assert "parallel_config" not in overrides
|
||||
|
||||
def test_strip_parent_engine_args_reports_only_surprising_parent_overrides(self):
|
||||
from dataclasses import fields as dc_fields
|
||||
|
||||
from vllm.engine.arg_utils import EngineArgs
|
||||
|
||||
parent_fields = {f.name: f for f in dc_fields(EngineArgs)}
|
||||
parent_fields = {f.name: f for f in fields(EngineArgs)}
|
||||
filtered, overridden = strip_parent_engine_args(
|
||||
{
|
||||
"model": "some/model",
|
||||
@@ -396,11 +400,7 @@ class TestStageResolutionHelpers:
|
||||
assert overridden == ["tensor_parallel_size"]
|
||||
|
||||
def test_strip_parent_engine_args_keeps_allowed_media_access_controls(self):
|
||||
from dataclasses import fields as dc_fields
|
||||
|
||||
from vllm.engine.arg_utils import EngineArgs
|
||||
|
||||
parent_fields = {f.name: f for f in dc_fields(EngineArgs)}
|
||||
parent_fields = {f.name: f for f in fields(EngineArgs)}
|
||||
filtered, overridden = strip_parent_engine_args(
|
||||
{
|
||||
"model": "some/model",
|
||||
@@ -826,8 +826,6 @@ class TestPipelineRegistry:
|
||||
|
||||
class TestDeployConfigLoading:
|
||||
def test_deploy_override_fields_include_deploy_schema_fields(self):
|
||||
from vllm_omni.config.stage_config import deploy_override_field_names
|
||||
|
||||
expected_fields = {
|
||||
"async_chunk",
|
||||
"async_scheduling",
|
||||
@@ -864,10 +862,6 @@ class TestDeployConfigLoading:
|
||||
)
|
||||
|
||||
def test_load_qwen3_omni_moe_deploy_config(self):
|
||||
from pathlib import Path
|
||||
|
||||
from vllm_omni.config.stage_config import load_deploy_config
|
||||
|
||||
deploy_path = Path(__file__).parent.parent / "vllm_omni" / "deploy" / "qwen3_omni_moe.yaml"
|
||||
deploy = load_deploy_config(deploy_path)
|
||||
assert len(deploy.stages) == 3
|
||||
@@ -876,10 +870,6 @@ class TestDeployConfigLoading:
|
||||
assert deploy.platforms is not None
|
||||
|
||||
def test_load_voxtral_tts_deploy_config_schema_fields(self):
|
||||
from pathlib import Path
|
||||
|
||||
from vllm_omni.config.stage_config import load_deploy_config
|
||||
|
||||
deploy_path = Path(__file__).parent.parent / "vllm_omni" / "deploy" / "voxtral_tts.yaml"
|
||||
deploy = load_deploy_config(deploy_path)
|
||||
assert deploy.stages[0].config_format == "mistral"
|
||||
@@ -890,21 +880,12 @@ class TestDeployConfigLoading:
|
||||
)
|
||||
|
||||
def test_load_ming_flash_omni_deploy_config_schema_fields(self):
|
||||
from pathlib import Path
|
||||
|
||||
from vllm_omni.config.stage_config import load_deploy_config
|
||||
|
||||
deploy_path = Path(__file__).parent.parent / "vllm_omni" / "deploy" / "ming_flash_omni.yaml"
|
||||
deploy = load_deploy_config(deploy_path)
|
||||
assert deploy.stages[0].compilation_config == {"pass_config": {"fuse_allreduce_rms": False}}
|
||||
assert "compilation_config" not in deploy.stages[0].engine_extras
|
||||
|
||||
def test_merge_pipeline_deploy(self):
|
||||
from pathlib import Path
|
||||
|
||||
import vllm_omni.model_executor.models.qwen3_omni.pipeline # noqa: F401
|
||||
from vllm_omni.config.stage_config import load_deploy_config, merge_pipeline_deploy
|
||||
|
||||
pipeline = _PIPELINE_REGISTRY["qwen3_omni_moe"]
|
||||
deploy_path = Path(__file__).parent.parent / "vllm_omni" / "deploy" / "qwen3_omni_moe.yaml"
|
||||
if not deploy_path.exists():
|
||||
@@ -921,11 +902,6 @@ class TestDeployConfigLoading:
|
||||
assert s0.yaml_extras["default_sampling_params"]["detokenize"] is True
|
||||
|
||||
def test_merge_pipeline_deploy_preserves_num_replicas(self, tmp_path):
|
||||
from pathlib import Path
|
||||
|
||||
import vllm_omni.model_executor.models.qwen3_omni.pipeline # noqa: F401
|
||||
from vllm_omni.config.stage_config import load_deploy_config, merge_pipeline_deploy
|
||||
|
||||
pipeline = _PIPELINE_REGISTRY["qwen3_omni_moe"]
|
||||
base = Path(__file__).parent.parent / "vllm_omni" / "deploy" / "qwen3_omni_moe.yaml"
|
||||
if not base.exists():
|
||||
@@ -942,15 +918,6 @@ class TestDeployConfigLoading:
|
||||
assert stages[1].yaml_runtime["num_replicas"] == 2
|
||||
|
||||
def test_merge_pipeline_deploy_preserves_requires_multimodal_data(self):
|
||||
from vllm_omni.config.stage_config import (
|
||||
DeployConfig,
|
||||
PipelineConfig,
|
||||
StageDeployConfig,
|
||||
StageExecutionType,
|
||||
StagePipelineConfig,
|
||||
merge_pipeline_deploy,
|
||||
)
|
||||
|
||||
pipeline = PipelineConfig(
|
||||
model_type="test_mm",
|
||||
model_arch="TestModel",
|
||||
@@ -969,11 +936,186 @@ class TestDeployConfigLoading:
|
||||
|
||||
assert stages[0].yaml_runtime["requires_multimodal_data"] is True
|
||||
|
||||
def test_mixed_schema_preserves_flat_fields(self):
|
||||
"""Ensure flat fields are not dropped when engine_args are present."""
|
||||
fake_config = {
|
||||
"stages": [
|
||||
{
|
||||
"stage_id": 0,
|
||||
"gpu_memory_utilization": 0.7,
|
||||
"max_num_seqs": 8,
|
||||
"engine_args": {
|
||||
"tensor_parallel_size": 4,
|
||||
"enforce_eager": True,
|
||||
},
|
||||
},
|
||||
]
|
||||
}
|
||||
|
||||
with patch("vllm_omni.config.stage_config.resolve_deploy_yaml", return_value=fake_config):
|
||||
deploy = load_deploy_config("dummy.yaml")
|
||||
|
||||
assert len(deploy.stages) == 1
|
||||
stage = deploy.stages[0]
|
||||
# Check that the engine args are set
|
||||
assert stage.tensor_parallel_size == 4
|
||||
assert stage.enforce_eager is True
|
||||
# Check that the other settings are also preserved
|
||||
assert stage.gpu_memory_utilization == 0.7
|
||||
assert stage.max_num_seqs == 8
|
||||
|
||||
def test_engine_parse_engine_fields(self):
|
||||
"""Test that we correctly parse & recursively merge stage deploy fields."""
|
||||
fake_config = {
|
||||
"stages": [
|
||||
{
|
||||
"stage_id": 0,
|
||||
"compilation_config": {
|
||||
"encoder_cudagraph_token_budgets": [1024, 2048],
|
||||
"pass_config": {"fuse_norm_quant": True},
|
||||
},
|
||||
"engine_args": {
|
||||
"compilation_config": {
|
||||
"cudagraph_mm_encoder": True,
|
||||
"pass_config": {"fuse_allreduce_rms": False},
|
||||
},
|
||||
},
|
||||
},
|
||||
]
|
||||
}
|
||||
|
||||
with patch("vllm_omni.config.stage_config.resolve_deploy_yaml", return_value=fake_config):
|
||||
deploy = load_deploy_config("dummy.yaml")
|
||||
|
||||
assert len(deploy.stages) == 1
|
||||
stage = deploy.stages[0]
|
||||
assert stage.compilation_config == {
|
||||
"encoder_cudagraph_token_budgets": [1024, 2048],
|
||||
"pass_config": {
|
||||
"fuse_norm_quant": True,
|
||||
"fuse_allreduce_rms": False,
|
||||
},
|
||||
"cudagraph_mm_encoder": True,
|
||||
}
|
||||
|
||||
def test_engine_extras_deep_merges_dicts_simple(self):
|
||||
"""Ensure dictionary valued keys merge properly for top level dicts."""
|
||||
fake_config = {
|
||||
"stages": [
|
||||
{
|
||||
"stage_id": 0,
|
||||
"foo": {"a": 111, "b": 1},
|
||||
"engine_args": {
|
||||
"foo": {"b": 2, "c": 3},
|
||||
},
|
||||
},
|
||||
]
|
||||
}
|
||||
|
||||
with patch("vllm_omni.config.stage_config.resolve_deploy_yaml", return_value=fake_config):
|
||||
deploy = load_deploy_config("dummy.yaml")
|
||||
|
||||
assert len(deploy.stages) == 1
|
||||
stage = deploy.stages[0]
|
||||
assert "foo" in stage.engine_extras
|
||||
assert stage.engine_extras["foo"] == {"a": 111, "b": 2, "c": 3}
|
||||
|
||||
def test_engine_extras_dict_type_mismatch(self):
|
||||
"""Ensure that we handle type mismatches with nested dicts correctly."""
|
||||
fake_config = {
|
||||
"stages": [
|
||||
{
|
||||
"stage_id": 0,
|
||||
"foo": {"b": {1: 1}},
|
||||
"engine_args": {
|
||||
"foo": {"b": 2},
|
||||
},
|
||||
},
|
||||
]
|
||||
}
|
||||
|
||||
with patch("vllm_omni.config.stage_config.resolve_deploy_yaml", return_value=fake_config):
|
||||
deploy = load_deploy_config("dummy.yaml")
|
||||
|
||||
assert len(deploy.stages) == 1
|
||||
stage = deploy.stages[0]
|
||||
assert "foo" in stage.engine_extras
|
||||
assert stage.engine_extras["foo"] == {"b": 2}
|
||||
|
||||
def test_mixed_engine_extras_deep_merges_dicts(self):
|
||||
"""Ensure dictionary valued keys merge properly for nested dicts."""
|
||||
fake_config = {
|
||||
"stages": [
|
||||
{
|
||||
"stage_id": 0,
|
||||
"foo": {"a": 111, "b": {"e": 199}},
|
||||
"engine_args": {
|
||||
"foo": {"b": {"d": 9}, "c": 3},
|
||||
},
|
||||
},
|
||||
]
|
||||
}
|
||||
|
||||
with patch("vllm_omni.config.stage_config.resolve_deploy_yaml", return_value=fake_config):
|
||||
deploy = load_deploy_config("dummy.yaml")
|
||||
|
||||
assert len(deploy.stages) == 1
|
||||
stage = deploy.stages[0]
|
||||
assert "foo" in stage.engine_extras
|
||||
assert stage.engine_extras["foo"] == {"a": 111, "b": {"d": 9, "e": 199}, "c": 3}
|
||||
|
||||
def test_deep_merge_does_not_mutate_inputs(self):
|
||||
"""Merging engine_args must not mutate the base stage dict."""
|
||||
fake_config = {
|
||||
"stages": [
|
||||
{
|
||||
"stage_id": 0,
|
||||
"foo": {"a": 1, "b": {"x": 10, "y": 20}},
|
||||
"engine_args": {
|
||||
"foo": {"b": {"y": 99, "z": 30}, "c": 3},
|
||||
},
|
||||
},
|
||||
]
|
||||
}
|
||||
original_foo = fake_config["stages"][0]["foo"]
|
||||
original_b = original_foo["b"]
|
||||
|
||||
with patch("vllm_omni.config.stage_config.resolve_deploy_yaml", return_value=fake_config):
|
||||
deploy = load_deploy_config("dummy.yaml")
|
||||
|
||||
# Values should merge into the new dict correctly
|
||||
assert deploy.stages[0].engine_extras["foo"] == {
|
||||
"a": 1,
|
||||
"b": {"x": 10, "y": 99, "z": 30},
|
||||
"c": 3,
|
||||
}
|
||||
# But the original nested dicts foo / b should be unchanged, since
|
||||
# we recursively shallow copy to avoid mutating in place.
|
||||
assert original_foo == {"a": 1, "b": {"x": 10, "y": 20}}
|
||||
assert original_b == {"x": 10, "y": 20}
|
||||
|
||||
def test_mixed_schema_engine_args_wins_scalars(self):
|
||||
"""engine_args takes precedence over flat fields for scalar conflicts."""
|
||||
fake_config = {
|
||||
"stages": [
|
||||
{
|
||||
"stage_id": 0,
|
||||
"gpu_memory_utilization": 0.7,
|
||||
"engine_args": {
|
||||
"gpu_memory_utilization": 0.5,
|
||||
},
|
||||
},
|
||||
]
|
||||
}
|
||||
|
||||
with patch("vllm_omni.config.stage_config.resolve_deploy_yaml", return_value=fake_config):
|
||||
deploy = load_deploy_config("dummy.yaml")
|
||||
|
||||
assert deploy.stages[0].gpu_memory_utilization == 0.5
|
||||
|
||||
|
||||
class TestQwen3OmniPipeline:
|
||||
def test_registered(self):
|
||||
import vllm_omni.model_executor.models.qwen3_omni.pipeline # noqa: F401
|
||||
|
||||
p = _PIPELINE_REGISTRY.get("qwen3_omni_moe")
|
||||
assert p is not None
|
||||
assert p.model_arch == "Qwen3OmniMoeForConditionalGeneration"
|
||||
@@ -981,8 +1123,6 @@ class TestQwen3OmniPipeline:
|
||||
assert p.validate() == []
|
||||
|
||||
def test_thinker(self):
|
||||
import vllm_omni.model_executor.models.qwen3_omni.pipeline # noqa: F401
|
||||
|
||||
s = _PIPELINE_REGISTRY["qwen3_omni_moe"].get_stage(0)
|
||||
assert s.model_stage == "thinker"
|
||||
assert s.execution_type == StageExecutionType.LLM_AR
|
||||
@@ -991,8 +1131,6 @@ class TestQwen3OmniPipeline:
|
||||
assert s.sampling_constraints["detokenize"] is True
|
||||
|
||||
def test_talker(self):
|
||||
import vllm_omni.model_executor.models.qwen3_omni.pipeline # noqa: F401
|
||||
|
||||
s = _PIPELINE_REGISTRY["qwen3_omni_moe"].get_stage(1)
|
||||
assert s.input_sources == (0,)
|
||||
assert s.sampling_constraints["stop_token_ids"] == [2150]
|
||||
@@ -1000,8 +1138,6 @@ class TestQwen3OmniPipeline:
|
||||
assert s.custom_process_next_stage_input_func is not None
|
||||
|
||||
def test_code2wav(self):
|
||||
import vllm_omni.model_executor.models.qwen3_omni.pipeline # noqa: F401
|
||||
|
||||
s = _PIPELINE_REGISTRY["qwen3_omni_moe"].get_stage(2)
|
||||
assert s.execution_type == StageExecutionType.LLM_GENERATION
|
||||
assert s.final_output_type == "audio"
|
||||
@@ -1010,8 +1146,6 @@ class TestQwen3OmniPipeline:
|
||||
|
||||
class TestQwen2_5OmniPipeline:
|
||||
def test_registered(self):
|
||||
import vllm_omni.model_executor.models.qwen2_5_omni.pipeline # noqa: F401
|
||||
|
||||
p = _PIPELINE_REGISTRY.get("qwen2_5_omni")
|
||||
assert p is not None
|
||||
assert p.model_arch == "Qwen2_5OmniForConditionalGeneration"
|
||||
@@ -1019,8 +1153,6 @@ class TestQwen2_5OmniPipeline:
|
||||
assert p.validate() == []
|
||||
|
||||
def test_thinker(self):
|
||||
import vllm_omni.model_executor.models.qwen2_5_omni.pipeline # noqa: F401
|
||||
|
||||
s = _PIPELINE_REGISTRY["qwen2_5_omni"].get_stage(0)
|
||||
assert s.model_stage == "thinker"
|
||||
assert s.execution_type == StageExecutionType.LLM_AR
|
||||
@@ -1029,16 +1161,12 @@ class TestQwen2_5OmniPipeline:
|
||||
assert s.requires_multimodal_data is True
|
||||
|
||||
def test_talker(self):
|
||||
import vllm_omni.model_executor.models.qwen2_5_omni.pipeline # noqa: F401
|
||||
|
||||
s = _PIPELINE_REGISTRY["qwen2_5_omni"].get_stage(1)
|
||||
assert s.input_sources == (0,)
|
||||
assert s.sampling_constraints["stop_token_ids"] == [8294]
|
||||
assert s.custom_process_input_func is not None
|
||||
|
||||
def test_code2wav(self):
|
||||
import vllm_omni.model_executor.models.qwen2_5_omni.pipeline # noqa: F401
|
||||
|
||||
s = _PIPELINE_REGISTRY["qwen2_5_omni"].get_stage(2)
|
||||
assert s.execution_type == StageExecutionType.LLM_GENERATION
|
||||
assert s.final_output_type == "audio"
|
||||
@@ -1047,8 +1175,6 @@ class TestQwen2_5OmniPipeline:
|
||||
|
||||
class TestQwen3TTSPipeline:
|
||||
def test_registered(self):
|
||||
import vllm_omni.model_executor.models.qwen3_tts.pipeline # noqa: F401
|
||||
|
||||
p = _PIPELINE_REGISTRY.get("qwen3_tts")
|
||||
assert p is not None
|
||||
assert p.model_arch == "Qwen3TTSTalkerForConditionalGeneration"
|
||||
@@ -1056,8 +1182,6 @@ class TestQwen3TTSPipeline:
|
||||
assert p.validate() == []
|
||||
|
||||
def test_talker_stage(self):
|
||||
import vllm_omni.model_executor.models.qwen3_tts.pipeline # noqa: F401
|
||||
|
||||
s = _PIPELINE_REGISTRY["qwen3_tts"].get_stage(0)
|
||||
assert s.model_stage == "qwen3_tts"
|
||||
assert s.execution_type == StageExecutionType.LLM_AR
|
||||
@@ -1068,8 +1192,6 @@ class TestQwen3TTSPipeline:
|
||||
assert s.model_arch is None
|
||||
|
||||
def test_code2wav_stage_has_per_stage_model_arch(self):
|
||||
import vllm_omni.model_executor.models.qwen3_tts.pipeline # noqa: F401
|
||||
|
||||
s = _PIPELINE_REGISTRY["qwen3_tts"].get_stage(1)
|
||||
assert s.execution_type == StageExecutionType.LLM_GENERATION
|
||||
assert s.final_output_type == "audio"
|
||||
@@ -1081,9 +1203,6 @@ class TestQwen3TTSPipeline:
|
||||
|
||||
def test_per_stage_model_arch_flows_through_merge(self, tmp_path):
|
||||
"""Verify the new ps.model_arch override survives merge_pipeline_deploy."""
|
||||
import vllm_omni.model_executor.models.qwen3_tts.pipeline # noqa: F401
|
||||
from vllm_omni.config.stage_config import load_deploy_config, merge_pipeline_deploy
|
||||
|
||||
deploy_path = Path(__file__).parent.parent / "vllm_omni" / "deploy" / "qwen3_tts.yaml"
|
||||
if not deploy_path.exists():
|
||||
pytest.skip("qwen3_tts deploy yaml not found")
|
||||
@@ -1099,8 +1218,6 @@ class TestQwen3TTSPipeline:
|
||||
|
||||
def test_subtalker_sampling_params_deep_merge_preserves_base_keys(self):
|
||||
"""Verify subtalker sampling params participate in stage deep-merge."""
|
||||
from vllm_omni.config.stage_config import _deep_merge_stage
|
||||
|
||||
base = {
|
||||
"stage_id": 0,
|
||||
"subtalker_sampling_params": {
|
||||
@@ -1130,8 +1247,6 @@ class TestQwen3TTSPipeline:
|
||||
|
||||
class TestMingFlashOmniPipeline:
|
||||
def test_registered(self):
|
||||
import vllm_omni.model_executor.models.ming_flash_omni.pipeline # noqa: F401
|
||||
|
||||
p = _PIPELINE_REGISTRY.get("ming_flash_omni")
|
||||
assert p is not None
|
||||
assert p.model_arch == "MingFlashOmniForConditionalGeneration"
|
||||
@@ -1139,8 +1254,6 @@ class TestMingFlashOmniPipeline:
|
||||
assert p.validate() == []
|
||||
|
||||
def test_thinker_stage(self):
|
||||
import vllm_omni.model_executor.models.ming_flash_omni.pipeline # noqa: F401
|
||||
|
||||
s = _PIPELINE_REGISTRY["ming_flash_omni"].get_stage(0)
|
||||
assert s.model_stage == "thinker"
|
||||
assert s.execution_type == StageExecutionType.LLM_AR
|
||||
@@ -1151,8 +1264,6 @@ class TestMingFlashOmniPipeline:
|
||||
assert s.sampling_constraints["detokenize"] is True
|
||||
|
||||
def test_talker_stage(self):
|
||||
import vllm_omni.model_executor.models.ming_flash_omni.pipeline # noqa: F401
|
||||
|
||||
s = _PIPELINE_REGISTRY["ming_flash_omni"].get_stage(1)
|
||||
assert s.model_stage == "ming_tts"
|
||||
assert s.execution_type == StageExecutionType.LLM_GENERATION
|
||||
@@ -1171,18 +1282,12 @@ class TestMingFlashOmniPipeline:
|
||||
Lazy string references only fail at first inference otherwise — this
|
||||
catches typos in the pipeline declaration at import / registration time.
|
||||
"""
|
||||
import importlib
|
||||
|
||||
import vllm_omni.model_executor.models.ming_flash_omni.pipeline # noqa: F401
|
||||
|
||||
s = _PIPELINE_REGISTRY["ming_flash_omni"].get_stage(1)
|
||||
module_path, _, attr = s.custom_process_input_func.rpartition(".")
|
||||
module = importlib.import_module(module_path)
|
||||
assert callable(getattr(module, attr))
|
||||
|
||||
def test_tts_pipeline_registered(self):
|
||||
import vllm_omni.model_executor.models.ming_flash_omni.pipeline # noqa: F401
|
||||
|
||||
p = _PIPELINE_REGISTRY.get("ming_flash_omni_tts")
|
||||
assert p is not None
|
||||
assert p.model_arch == "MingFlashOmniTalkerForConditionalGeneration"
|
||||
@@ -1190,8 +1295,6 @@ class TestMingFlashOmniPipeline:
|
||||
assert p.validate() == []
|
||||
|
||||
def test_tts_stage(self):
|
||||
import vllm_omni.model_executor.models.ming_flash_omni.pipeline # noqa: F401
|
||||
|
||||
s = _PIPELINE_REGISTRY["ming_flash_omni_tts"].get_stage(0)
|
||||
assert s.model_stage == "ming_tts"
|
||||
assert s.execution_type == StageExecutionType.LLM_GENERATION
|
||||
@@ -1204,9 +1307,6 @@ class TestMingFlashOmniPipeline:
|
||||
|
||||
def test_full_yaml_loads_and_merges(self):
|
||||
"""deploy/ming_flash_omni.yaml parses and merges with the registered pipeline."""
|
||||
import vllm_omni.model_executor.models.ming_flash_omni.pipeline # noqa: F401
|
||||
from vllm_omni.config.stage_config import load_deploy_config, merge_pipeline_deploy
|
||||
|
||||
deploy_path = Path(__file__).parent.parent / "vllm_omni" / "deploy" / "ming_flash_omni.yaml"
|
||||
if not deploy_path.exists():
|
||||
pytest.skip("ming_flash_omni deploy yaml not found")
|
||||
@@ -1226,9 +1326,6 @@ class TestMingFlashOmniPipeline:
|
||||
|
||||
def test_tts_yaml_loads_and_merges(self):
|
||||
"""deploy/ming_flash_omni_tts.yaml parses and routes to the TTS-only pipeline."""
|
||||
import vllm_omni.model_executor.models.ming_flash_omni.pipeline # noqa: F401
|
||||
from vllm_omni.config.stage_config import load_deploy_config, merge_pipeline_deploy
|
||||
|
||||
deploy_path = Path(__file__).parent.parent / "vllm_omni" / "deploy" / "ming_flash_omni_tts.yaml"
|
||||
if not deploy_path.exists():
|
||||
pytest.skip("ming_flash_omni_tts deploy yaml not found")
|
||||
@@ -1243,8 +1340,6 @@ class TestMingFlashOmniPipeline:
|
||||
assert stages[0].yaml_engine_args["model_arch"] == "MingFlashOmniTalkerForConditionalGeneration"
|
||||
|
||||
def test_thinker_only_pipeline_registered(self):
|
||||
import vllm_omni.model_executor.models.ming_flash_omni.pipeline # noqa: F401
|
||||
|
||||
p = _PIPELINE_REGISTRY.get("ming_flash_omni_thinker_only")
|
||||
assert p is not None
|
||||
assert p.model_arch == "MingFlashOmniForConditionalGeneration"
|
||||
@@ -1252,8 +1347,6 @@ class TestMingFlashOmniPipeline:
|
||||
assert p.validate() == []
|
||||
|
||||
def test_thinker_only_stage(self):
|
||||
import vllm_omni.model_executor.models.ming_flash_omni.pipeline # noqa: F401
|
||||
|
||||
s = _PIPELINE_REGISTRY["ming_flash_omni_thinker_only"].get_stage(0)
|
||||
assert s.model_stage == "thinker"
|
||||
assert s.execution_type == StageExecutionType.LLM_AR
|
||||
@@ -1267,9 +1360,6 @@ class TestMingFlashOmniPipeline:
|
||||
|
||||
def test_thinker_only_yaml_loads_and_merges(self):
|
||||
"""deploy/ming_flash_omni_thinker_only.yaml parses and routes to the thinker-only pipeline."""
|
||||
import vllm_omni.model_executor.models.ming_flash_omni.pipeline # noqa: F401
|
||||
from vllm_omni.config.stage_config import load_deploy_config, merge_pipeline_deploy
|
||||
|
||||
deploy_path = Path(__file__).parent.parent / "vllm_omni" / "deploy" / "ming_flash_omni_thinker_only.yaml"
|
||||
if not deploy_path.exists():
|
||||
pytest.skip("ming_flash_omni_thinker_only deploy yaml not found")
|
||||
@@ -1288,9 +1378,6 @@ class TestBaseConfigInheritance:
|
||||
"""Test deploy YAML base_config inheritance."""
|
||||
|
||||
def test_ci_inherits_from_main(self):
|
||||
from tests.helpers.stage_config import get_deploy_config_path
|
||||
from vllm_omni.config.stage_config import load_deploy_config
|
||||
|
||||
ci_path = Path(get_deploy_config_path("ci/qwen3_omni_moe.yaml"))
|
||||
if not ci_path.exists():
|
||||
pytest.skip("CI deploy config not found")
|
||||
@@ -1298,7 +1385,7 @@ class TestBaseConfigInheritance:
|
||||
deploy = load_deploy_config(ci_path)
|
||||
assert len(deploy.stages) == 3
|
||||
# CI overrides
|
||||
assert deploy.stages[0].load_format == "dummy"
|
||||
assert deploy.stages[0].load_format is None
|
||||
assert "load_format" not in deploy.stages[0].engine_extras
|
||||
assert deploy.stages[0].max_num_seqs == 5
|
||||
# Inherited from base
|
||||
@@ -1311,9 +1398,6 @@ class TestBaseConfigInheritance:
|
||||
assert deploy.async_chunk is False
|
||||
|
||||
def test_ci_sampling_merge(self):
|
||||
from tests.helpers.stage_config import get_deploy_config_path
|
||||
from vllm_omni.config.stage_config import load_deploy_config
|
||||
|
||||
ci_path = Path(get_deploy_config_path("ci/qwen3_omni_moe.yaml"))
|
||||
if not ci_path.exists():
|
||||
pytest.skip("CI deploy config not found")
|
||||
@@ -1328,8 +1412,6 @@ class TestBaseConfigInheritance:
|
||||
|
||||
def test_pure_inheritance_overlay(self, tmp_path):
|
||||
"""An overlay with only ``base_config`` inherits everything."""
|
||||
from vllm_omni.config.stage_config import load_deploy_config
|
||||
|
||||
base = Path(__file__).parent.parent / "vllm_omni" / "deploy" / "qwen3_omni_moe.yaml"
|
||||
if not base.exists():
|
||||
pytest.skip("Base deploy config not found")
|
||||
@@ -1343,8 +1425,6 @@ class TestBaseConfigInheritance:
|
||||
|
||||
def test_single_field_overlay(self, tmp_path):
|
||||
"""An overlay overriding one stage field merges with the base."""
|
||||
from vllm_omni.config.stage_config import load_deploy_config
|
||||
|
||||
base = Path(__file__).parent.parent / "vllm_omni" / "deploy" / "qwen3_omni_moe.yaml"
|
||||
if not base.exists():
|
||||
pytest.skip("Base deploy config not found")
|
||||
@@ -1362,10 +1442,6 @@ class TestPlatformOverrides:
|
||||
"""Test platform-specific deploy config overrides."""
|
||||
|
||||
def test_npu_overrides(self):
|
||||
from pathlib import Path
|
||||
|
||||
from vllm_omni.config.stage_config import _apply_platform_overrides, load_deploy_config
|
||||
|
||||
deploy_path = Path(__file__).parent.parent / "vllm_omni" / "deploy" / "qwen3_omni_moe.yaml"
|
||||
if not deploy_path.exists():
|
||||
pytest.skip("Deploy config not found")
|
||||
@@ -1380,10 +1456,6 @@ class TestPlatformOverrides:
|
||||
assert deploy.stages[2].enforce_eager is True
|
||||
|
||||
def test_xpu_overrides(self):
|
||||
from pathlib import Path
|
||||
|
||||
from vllm_omni.config.stage_config import _apply_platform_overrides, load_deploy_config
|
||||
|
||||
deploy_path = Path(__file__).parent.parent / "vllm_omni" / "deploy" / "qwen3_omni_moe.yaml"
|
||||
if not deploy_path.exists():
|
||||
pytest.skip("Deploy config not found")
|
||||
@@ -1396,10 +1468,6 @@ class TestPlatformOverrides:
|
||||
assert deploy.stages[0].engine_extras.get("max_cudagraph_capture_size") == 0
|
||||
|
||||
def test_unknown_platform_noop(self):
|
||||
from pathlib import Path
|
||||
|
||||
from vllm_omni.config.stage_config import _apply_platform_overrides, load_deploy_config
|
||||
|
||||
deploy_path = Path(__file__).parent.parent / "vllm_omni" / "deploy" / "qwen3_omni_moe.yaml"
|
||||
if not deploy_path.exists():
|
||||
pytest.skip("Deploy config not found")
|
||||
@@ -1411,8 +1479,6 @@ class TestPlatformOverrides:
|
||||
|
||||
def test_platforms_deep_merge_inheritance(self, tmp_path):
|
||||
"""Overlay's platforms: block layers onto base's, per-stage."""
|
||||
from vllm_omni.config.stage_config import _apply_platform_overrides, load_deploy_config
|
||||
|
||||
base = tmp_path / "base.yaml"
|
||||
base.write_text(
|
||||
"stages:\n"
|
||||
@@ -1447,11 +1513,6 @@ class TestCLIOverrideFlow:
|
||||
"""Test --stage-overrides JSON merge into StageConfig."""
|
||||
|
||||
def test_stage_overrides_merge(self):
|
||||
from pathlib import Path
|
||||
|
||||
import vllm_omni.model_executor.models.qwen3_omni.pipeline # noqa: F401
|
||||
from vllm_omni.config.stage_config import load_deploy_config, merge_pipeline_deploy
|
||||
|
||||
pipeline = _PIPELINE_REGISTRY["qwen3_omni_moe"]
|
||||
deploy_path = Path(__file__).parent.parent / "vllm_omni" / "deploy" / "qwen3_omni_moe.yaml"
|
||||
if not deploy_path.exists():
|
||||
@@ -1466,11 +1527,6 @@ class TestCLIOverrideFlow:
|
||||
assert stages[0].runtime_overrides["gpu_memory_utilization"] == 0.5
|
||||
|
||||
def test_global_override_applies_to_all(self):
|
||||
from pathlib import Path
|
||||
|
||||
import vllm_omni.model_executor.models.qwen3_omni.pipeline # noqa: F401
|
||||
from vllm_omni.config.stage_config import load_deploy_config, merge_pipeline_deploy
|
||||
|
||||
pipeline = _PIPELINE_REGISTRY["qwen3_omni_moe"]
|
||||
deploy_path = Path(__file__).parent.parent / "vllm_omni" / "deploy" / "qwen3_omni_moe.yaml"
|
||||
if not deploy_path.exists():
|
||||
@@ -1490,8 +1546,6 @@ class TestSentinelDefaultPrecedence:
|
||||
to YAML / dataclass defaults (#3035)."""
|
||||
|
||||
def _stages(self, cli_overrides):
|
||||
import vllm_omni.model_executor.models.qwen3_omni.pipeline # noqa: F401
|
||||
|
||||
return StageConfigFactory._create_from_registry(
|
||||
"qwen3_omni_moe",
|
||||
cli_overrides=cli_overrides,
|
||||
@@ -1504,7 +1558,7 @@ class TestSentinelDefaultPrecedence:
|
||||
def test_none_value_skipped_yaml_wins(self):
|
||||
stages = self._stages({"max_num_seqs": None})
|
||||
assert stages[2].runtime_overrides.get("max_num_seqs") is None
|
||||
assert stages[2].yaml_engine_args["max_num_seqs"] == 64
|
||||
assert stages[2].yaml_engine_args.get("max_num_seqs") == 64
|
||||
|
||||
def test_empty_kwargs_yaml_only(self):
|
||||
stages = self._stages({})
|
||||
@@ -1550,15 +1604,11 @@ class TestSentinelDefaultPrecedence:
|
||||
assert stage.runtime_overrides == {}
|
||||
|
||||
def test_create_from_registry_no_cli_explicit_keys_param(self):
|
||||
import inspect
|
||||
|
||||
sig = inspect.signature(StageConfigFactory._create_from_registry)
|
||||
named = [p for p in sig.parameters.values() if p.kind != p.VAR_KEYWORD]
|
||||
assert "cli_explicit_keys" not in {p.name for p in named}
|
||||
|
||||
def test_cli_explicit_keys_kwarg_emits_deprecation(self):
|
||||
import vllm_omni.model_executor.models.qwen3_omni.pipeline # noqa: F401
|
||||
|
||||
with warnings.catch_warnings(record=True) as w:
|
||||
warnings.simplefilter("always")
|
||||
StageConfigFactory._create_from_registry(
|
||||
@@ -1572,13 +1622,6 @@ class TestSentinelDefaultPrecedence:
|
||||
"""A single ``qwen3_tts`` pipeline picks per-chunk vs end-to-end
|
||||
processors based on ``deploy.async_chunk``, without needing a
|
||||
separate variant pipeline registration."""
|
||||
import vllm_omni.model_executor.models.qwen3_tts.pipeline # noqa: F401
|
||||
from vllm_omni.config.stage_config import (
|
||||
_PIPELINE_REGISTRY,
|
||||
DeployConfig,
|
||||
merge_pipeline_deploy,
|
||||
)
|
||||
|
||||
pipeline = _PIPELINE_REGISTRY["qwen3_tts"]
|
||||
|
||||
# async_chunk=True → stage 0's per-chunk processor wires up, stage 1
|
||||
@@ -1638,11 +1681,6 @@ class TestSamplingConstraintsPrecedence:
|
||||
"""Test that pipeline sampling_constraints override deploy defaults."""
|
||||
|
||||
def test_constraints_win(self):
|
||||
from pathlib import Path
|
||||
|
||||
import vllm_omni.model_executor.models.qwen3_omni.pipeline # noqa: F401
|
||||
from vllm_omni.config.stage_config import load_deploy_config, merge_pipeline_deploy
|
||||
|
||||
pipeline = _PIPELINE_REGISTRY["qwen3_omni_moe"]
|
||||
deploy_path = Path(__file__).parent.parent / "vllm_omni" / "deploy" / "qwen3_omni_moe.yaml"
|
||||
if not deploy_path.exists():
|
||||
|
||||
@@ -473,7 +473,7 @@ class DeployConfig:
|
||||
pipeline_parallel_size: int | None = None
|
||||
|
||||
|
||||
_STAGE_NON_ENGINE_KEYS = frozenset(
|
||||
_STAGE_RESERVED_KEYS = frozenset(
|
||||
{
|
||||
"stage_id",
|
||||
"devices",
|
||||
@@ -482,24 +482,31 @@ _STAGE_NON_ENGINE_KEYS = frozenset(
|
||||
"input_connectors",
|
||||
"default_sampling_params",
|
||||
"engine_extras",
|
||||
"engine_args",
|
||||
"runtime",
|
||||
}
|
||||
)
|
||||
|
||||
# Fields on StageDeployConfig that are populated from engine_args dict
|
||||
_STAGE_DEPLOY_FIELDS = {f.name: f for f in fields(StageDeployConfig) if f.name not in _STAGE_NON_ENGINE_KEYS}
|
||||
_STAGE_DEPLOY_FIELDS = {f.name: f for f in fields(StageDeployConfig) if f.name not in _STAGE_RESERVED_KEYS}
|
||||
|
||||
|
||||
def _parse_stage_deploy(stage_data: dict[str, Any]) -> StageDeployConfig:
|
||||
"""Parse a single stage entry from deploy YAML into StageDeployConfig."""
|
||||
# Get the non-reserved keys for this stage
|
||||
flat_args = {k: v for k, v in stage_data.items() if k not in _STAGE_RESERVED_KEYS}
|
||||
runtime_cfg = dict(stage_data.get("runtime", {}))
|
||||
devices = runtime_cfg.get("devices", stage_data.get("devices"))
|
||||
num_replicas = runtime_cfg.get("num_replicas", stage_data.get("num_replicas", 1))
|
||||
|
||||
if "engine_args" in stage_data:
|
||||
runtime_cfg = dict(stage_data.get("runtime", {}))
|
||||
engine_args = dict(stage_data["engine_args"])
|
||||
devices = stage_data.get("runtime", {}).get("devices", stage_data.get("devices"))
|
||||
num_replicas = runtime_cfg.get("num_replicas", stage_data.get("num_replicas", 1))
|
||||
else:
|
||||
engine_args = {k: v for k, v in stage_data.items() if k not in _STAGE_NON_ENGINE_KEYS and k != "stage_id"}
|
||||
devices = stage_data.get("devices")
|
||||
num_replicas = stage_data.get("num_replicas", stage_data.get("runtime", {}).get("num_replicas", 1))
|
||||
for k, v in stage_data["engine_args"].items():
|
||||
existing = flat_args.get(k)
|
||||
# If we have multiple dictionaries, merge recursively.
|
||||
if isinstance(v, dict) and isinstance(existing, dict):
|
||||
flat_args[k] = _get_recursively_merged_dict(existing, v)
|
||||
else:
|
||||
flat_args[k] = v
|
||||
|
||||
kwargs: dict[str, Any] = {
|
||||
"stage_id": stage_data["stage_id"],
|
||||
@@ -507,13 +514,13 @@ def _parse_stage_deploy(stage_data: dict[str, Any]) -> StageDeployConfig:
|
||||
"num_replicas": int(num_replicas),
|
||||
}
|
||||
for name, f in _STAGE_DEPLOY_FIELDS.items():
|
||||
if name in engine_args:
|
||||
kwargs[name] = engine_args.pop(name)
|
||||
if name in flat_args:
|
||||
kwargs[name] = flat_args.pop(name)
|
||||
|
||||
kwargs["output_connectors"] = stage_data.get("output_connectors")
|
||||
kwargs["input_connectors"] = stage_data.get("input_connectors")
|
||||
kwargs["default_sampling_params"] = stage_data.get("default_sampling_params")
|
||||
kwargs["engine_extras"] = engine_args
|
||||
kwargs["engine_extras"] = flat_args
|
||||
return StageDeployConfig(**kwargs)
|
||||
|
||||
|
||||
@@ -522,24 +529,34 @@ _DEEP_MERGE_KEYS = frozenset({"default_sampling_params", "subtalker_sampling_par
|
||||
|
||||
def _deep_merge_stage(base: dict, overlay: dict) -> dict:
|
||||
"""Deep-merge ``_DEEP_MERGE_KEYS`` so thin overlays don't drop base keys."""
|
||||
merged = dict(base)
|
||||
for k, v in overlay.items():
|
||||
if k in _DEEP_MERGE_KEYS:
|
||||
base_val = merged.get(k)
|
||||
if isinstance(v, dict) and isinstance(base_val, dict):
|
||||
merged[k] = {**base_val, **v}
|
||||
continue
|
||||
# Deep-merge key but at least one side isn't a dict: surface the
|
||||
# silent clobber so mismatched YAML types don't get past review.
|
||||
if base_val is not None:
|
||||
# Deep merge _DEEP_MERGE_KEYS recursively
|
||||
base_merge_dict = {k: v for k, v in base.items() if k in _DEEP_MERGE_KEYS}
|
||||
overlay_merge_dict = {k: v for k, v in overlay.items() if k in _DEEP_MERGE_KEYS}
|
||||
|
||||
# Get the merge dict; priority is base < overlay < merged sub
|
||||
merged_subdict = _get_recursively_merged_dict(original=base_merge_dict, update=overlay_merge_dict)
|
||||
merged_dict = {**base, **overlay, **merged_subdict}
|
||||
return merged_dict
|
||||
|
||||
|
||||
def _get_recursively_merged_dict(original: dict, update: dict) -> dict:
|
||||
"""Recursively merge two dicts, returning a new dict."""
|
||||
merged = original.copy()
|
||||
for k, update_v in update.items():
|
||||
orig_v = merged.get(k)
|
||||
if isinstance(orig_v, dict) and isinstance(update_v, dict):
|
||||
merged[k] = _get_recursively_merged_dict(orig_v, update_v)
|
||||
else:
|
||||
if orig_v is not None and (isinstance(orig_v, dict) != isinstance(update_v, dict)):
|
||||
logger.warning(
|
||||
"Deep-merge key %r has non-dict value (base=%s, overlay=%s); "
|
||||
"overlay will fully replace base instead of merging.",
|
||||
k,
|
||||
type(base_val).__name__,
|
||||
type(v).__name__,
|
||||
type(orig_v).__name__,
|
||||
type(update_v).__name__,
|
||||
)
|
||||
merged[k] = v
|
||||
|
||||
merged[k] = update_v
|
||||
return merged
|
||||
|
||||
|
||||
@@ -779,7 +796,7 @@ def _build_engine_args(
|
||||
# Per-stage StageDeployConfig values override pipeline-wide settings.
|
||||
if ds is not None:
|
||||
for k, v in asdict(ds).items():
|
||||
if k in _STAGE_NON_ENGINE_KEYS or v is None:
|
||||
if k in _STAGE_RESERVED_KEYS or v is None:
|
||||
continue
|
||||
engine_args[k] = v
|
||||
engine_args.update(ds.engine_extras)
|
||||
|
||||
Reference in new issue
Block a user