[Refactor/Bugfix] Use Delta Messages for Streaming (#2911)

Signed-off-by: Alex Brooks <albrooks@redhat.com>
Signed-off-by: Sy03 <1370724210@qq.com>
Signed-off-by: Yueqian Lin <linyueqian@outlook.com>
Signed-off-by: Yueqian Lin <70319226+linyueqian@users.noreply.github.com>
Co-authored-by: Sy03 <1370724210@qq.com>
Co-authored-by: Yueqian Lin <linyueqian@outlook.com>
Co-authored-by: Yueqian Lin <70319226+linyueqian@users.noreply.github.com>
This commit is contained in:
authored and GitHub committed 2026-04-26 15:11:53 +12:00
1 parent 6e35bfbbae
commit e03ab82dd2
27 files changed
+623 -177

No files matched your search

+43
View File
@@ -7,6 +7,7 @@ from dataclasses import dataclass
import pytest
import torch
from pytest_mock import MockerFixture
from vllm.sampling_params import RequestOutputKind, SamplingParams
from vllm_omni.config.yaml_util import create_config
from vllm_omni.diffusion.data import OmniDiffusionConfig
@@ -15,6 +16,7 @@ from vllm_omni.engine.async_omni_engine import AsyncOmniEngine
from vllm_omni.entrypoints.utils import (
_convert_dataclasses_to_dict,
_filter_dict_like_object,
coerce_param_message_types,
filter_dataclass_kwargs,
load_and_resolve_stage_configs,
load_stage_configs_from_yaml,
@@ -424,3 +426,44 @@ class TestLoadStageConfigsFromYaml:
assert stages[0]["engine_args"]["nested"]["base"] == 1
assert stages[0]["engine_args"]["nested"]["override"] == 2
class TestCumulativeStreamingCoercion:
@pytest.mark.parametrize("skip_clone", [True, False])
def test_cumulative_default_becomes_delta_if_stream(self, skip_clone):
"""Ensure cumulative messages are coercible to delta if streaming."""
sp = SamplingParams(output_kind=RequestOutputKind.CUMULATIVE)
sp.skip_clone = skip_clone
result = coerce_param_message_types([sp], is_streaming=True)[0]
assert isinstance(result, SamplingParams)
assert result.output_kind == RequestOutputKind.DELTA
assert (skip_clone and sp is result) or (not skip_clone and sp is not result)
@pytest.mark.parametrize("skip_clone", [True, False])
def test_cumulative_default_becomes_final_only_if_not_stream(self, skip_clone):
"""Ensure cumulative messages are coercible to final only if not streaming."""
sp = SamplingParams(output_kind=RequestOutputKind.CUMULATIVE)
sp.skip_clone = skip_clone
result = coerce_param_message_types([sp], is_streaming=False)[0]
assert isinstance(result, SamplingParams)
assert result.output_kind == RequestOutputKind.FINAL_ONLY
assert (skip_clone and sp is result) or (not skip_clone and sp is not result)
@pytest.mark.parametrize("is_streaming", [True, False])
@pytest.mark.parametrize("output_kind", [RequestOutputKind.DELTA, RequestOutputKind.FINAL_ONLY])
def test_non_cumulative_are_coerced(self, output_kind, is_streaming):
"""Ensure non-cumulative params are coerced to the target type."""
sp = SamplingParams(output_kind=output_kind)
expected = RequestOutputKind.DELTA if is_streaming else RequestOutputKind.FINAL_ONLY
result = coerce_param_message_types([sp], is_streaming=is_streaming)[0]
assert isinstance(result, SamplingParams)
assert result.output_kind == expected
def test_coercion_applies_to_all_stages(self):
"""Ensure all stages are coerced to DELTA for streaming."""
sp0 = SamplingParams(output_kind=RequestOutputKind.CUMULATIVE)
sp1 = SamplingParams(output_kind=RequestOutputKind.CUMULATIVE)
result = coerce_param_message_types([sp0, sp1], is_streaming=True)
assert all([isinstance(r, SamplingParams) for r in result])
assert result[0].output_kind == RequestOutputKind.DELTA
assert result[1].output_kind == RequestOutputKind.DELTA