[Config] Add HunyuanImage3 deploy configs (#3172)

Signed-off-by: KexiongYu <yukexiong1@huawei.com>
Signed-off-by: Y. Fisher <yukexiong1@huawei.com>
This commit is contained in:
Y. Fisher authored and GitHub committed 2026-05-11 22:49:19 +08:00
1 parent c9a8556c24
commit a33e2eb588
26 files changed
+672 -742

No files matched your search

@@ -24,9 +24,11 @@ import pathlib
import pytest
from vllm_omni.diffusion.models.hunyuan_image3.prompt_utils import (
HUNYUAN_IMAGE3_SPECIAL_TOKEN_IDS,
available_tasks,
build_prompt,
build_prompt_tokens,
resolve_stop_token_ids,
)
pytestmark = [pytest.mark.core_model, pytest.mark.cpu]
@@ -38,7 +40,7 @@ pytestmark = [pytest.mark.core_model, pytest.mark.cpu]
class FakeTokenizer:
"""Minimal tokenizer stub that records every encode() call.
Returns deterministic ids: special tokens map to small ints (1-4),
Returns deterministic ids from convert_tokens_to_ids while
encode() returns one id per character starting at 100. This lets
tests both verify segmentation (by inspecting `encode_calls`) and
locate substrings inside the returned id list.
@@ -49,10 +51,17 @@ class FakeTokenizer:
"<img>": 2,
"<think>": 3,
"<recaption>": 4,
"<|endoftext|>": 5,
"</recaption>": 6,
"</answer>": 7,
"<boi>": 8,
"</think>": 9,
**{f"<img_ratio_{i}>": 1000 + i for i in range(33)},
}
def __init__(self) -> None:
self.encode_calls: list[str] = []
self.eos_token_id = self.SPECIAL["<|endoftext|>"]
def convert_tokens_to_ids(self, tok: str) -> int:
return self.SPECIAL.get(tok, 0)
@@ -75,6 +84,14 @@ def test_available_tasks_covers_all_modalities():
}
def test_resolve_stop_token_ids_uses_answer_for_generation_tasks():
tok = FakeTokenizer()
answer_id = HUNYUAN_IMAGE3_SPECIAL_TOKEN_IDS["<answer>"]
assert resolve_stop_token_ids(task="t2i_think", tokenizer=tok) == [answer_id]
assert resolve_stop_token_ids(task="t2i_recaption", tokenizer=tok) == [answer_id]
@pytest.mark.parametrize(
"task",
[
@@ -164,19 +181,24 @@ def test_build_prompt_tokens_segments_each_boundary():
def test_build_prompt_tokens_image_placeholder_present_for_image_tasks():
tok = FakeTokenizer()
ids = build_prompt_tokens("hi", tok, task="i2t")
assert ids[0] == 1, "BOS (<|startoftext|>) must be the first token"
assert 2 in ids, "<img> placeholder must be present for i2t/it2i tasks"
assert ids[0] == FakeTokenizer.SPECIAL["<|startoftext|>"], "BOS (<|startoftext|>) must be the first token"
assert FakeTokenizer.SPECIAL["<img>"] in ids, "<img> placeholder must be present for i2t/it2i tasks"
def test_build_prompt_tokens_no_image_for_text_only_tasks():
tok = FakeTokenizer()
ids = build_prompt_tokens("hi", tok, task="t2t")
assert 2 not in ids, "<img> must NOT appear for text-only tasks"
assert FakeTokenizer.SPECIAL["<img>"] not in ids, "<img> must NOT appear for text-only tasks"
@pytest.mark.parametrize(
"task,trigger_id",
[("it2i_think", 3), ("t2i_think", 3), ("it2i_recaption", 4), ("t2i_recaption", 4)],
[
("it2i_think", FakeTokenizer.SPECIAL["<think>"]),
("t2i_think", FakeTokenizer.SPECIAL["<think>"]),
("it2i_recaption", FakeTokenizer.SPECIAL["<recaption>"]),
("t2i_recaption", FakeTokenizer.SPECIAL["<recaption>"]),
],
)
def test_build_prompt_tokens_trigger_is_last_token(task: str, trigger_id: int):
"""Trigger tag id must be the LAST token (after `Assistant: ` segment)."""
@@ -189,7 +211,10 @@ def test_build_prompt_tokens_no_trigger_for_plain_tasks():
"""Tasks without trigger_tag (t2t / i2t) must NOT append a trigger id."""
tok = FakeTokenizer()
ids = build_prompt_tokens("hi", tok, task="t2t")
assert ids[-1] not in {3, 4} # neither <think> nor <recaption>
assert ids[-1] not in {
FakeTokenizer.SPECIAL["<think>"],
FakeTokenizer.SPECIAL["<recaption>"],
}
# -------------------- end2end.py wiring guard --------------------
@@ -234,10 +259,16 @@ def test_end2end_routes_through_shared_prompt_utils():
for node in ast.walk(tree):
if isinstance(node, ast.ImportFrom) and node.module and node.module.endswith("hunyuan_image3.prompt_utils"):
imported_from_prompt_utils.update(alias.name for alias in node.names)
assert "build_prompt_tokens" in imported_from_prompt_utils, (
"end2end.py must import build_prompt_tokens from "
expected_imports = {
"_TASK_PRESETS",
"build_prompt_tokens",
"resolve_stop_token_ids",
}
assert expected_imports <= imported_from_prompt_utils, (
"end2end.py must import the HunyuanImage3 prompt and stop-token helpers from "
"vllm_omni.diffusion.models.hunyuan_image3.prompt_utils -- the shared "
"helper is the single source of truth for the AR-prefill template."
"module is the single source of truth for the AR-prefill template and "
"bot_task-derived AR stop token ids."
)
@@ -1,6 +1,5 @@
# ruff: noqa: E501
from collections.abc import Generator
from pathlib import Path
import pytest
import torch
@@ -9,6 +8,7 @@ from PIL import Image
from transformers import CLIPModel, CLIPProcessor
from tests.helpers.runtime import OmniRunner
from tests.helpers.stage_config import get_deploy_config_path
from vllm_omni import Omni
from vllm_omni.inputs.data import OmniDiffusionSamplingParams
from vllm_omni.platforms import current_omni_platform
@@ -16,8 +16,7 @@ from vllm_omni.platforms import current_omni_platform
PROMPT = "A brown and white dog is running on the grass"
MODEL_NAME = "tencent/HunyuanImage-3.0"
LOCAL_CLIP_PATH = "openai/clip-vit-base-patch32"
REPO_ROOT = Path(__file__).resolve().parents[3]
STAGE_CONFIG_PATH = REPO_ROOT / "vllm_omni" / "model_executor" / "stage_configs" / "hunyuan_image3_t2i.yaml"
DEPLOY_CONFIG_PATH = get_deploy_config_path("hunyuan_image3.yaml")
pytestmark = [pytest.mark.advanced_model, pytest.mark.diffusion]
@@ -274,7 +273,8 @@ def clip_bundle() -> tuple[CLIPModel, CLIPProcessor]:
def omni() -> Generator[Omni, None, None]:
with OmniRunner(
MODEL_NAME,
stage_configs_path=str(STAGE_CONFIG_PATH),
deploy_config=str(DEPLOY_CONFIG_PATH),
mode="text-to-image",
) as runner:
yield runner.omni
+39
View File
@@ -18,6 +18,7 @@ from vllm_omni.entrypoints.utils import (
_filter_dict_like_object,
coerce_param_message_types,
filter_dataclass_kwargs,
filter_stages,
load_and_resolve_stage_configs,
load_stage_configs_from_yaml,
resolve_model_config_path,
@@ -401,6 +402,44 @@ class TestLoadAndResolveStageConfigs:
assert stage_configs[1].runtime.num_replicas == 3
assert stage_configs[1].runtime.devices == "1,2,3"
def test_filter_stages_selects_mode_stages_without_mutating_stage_config(self, tmp_path):
config_path = tmp_path / "deploy.yaml"
config_path.write_text(
"""modes:
- mode: text-to-text
stages: [0]
- mode: text-to-image
stages: [0, 1]
""",
encoding="utf-8",
)
stages = [
create_config(
{
"stage_id": 0,
"runtime": {"requires_multimodal_data": True},
"final_output": False,
"final_output_type": None,
}
),
create_config(
{
"stage_id": 1,
"runtime": {"requires_multimodal_data": True},
"final_output": True,
"final_output_type": "image",
}
),
]
filtered = filter_stages(str(config_path), stages, {"mode": "text-to-text"})
assert len(filtered) == 1
assert filtered[0].stage_id == 0
assert filtered[0].runtime.requires_multimodal_data is True
assert filtered[0].final_output is False
assert filtered[0].final_output_type is None
class TestLoadStageConfigsFromYaml:
"""Regression tests for stage-config loading and merging."""
+28
View File
@@ -941,6 +941,34 @@ class TestDeployConfigLoading:
assert stages[1].yaml_runtime["devices"] == "1,2"
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",
stages=(
StagePipelineConfig(
stage_id=0,
model_stage="ar",
execution_type=StageExecutionType.LLM_AR,
requires_multimodal_data=True,
),
),
)
deploy = DeployConfig(async_chunk=False, stages=[StageDeployConfig(stage_id=0)])
stages = merge_pipeline_deploy(pipeline, deploy)
assert stages[0].yaml_runtime["requires_multimodal_data"] is True
class TestQwen3OmniPipeline:
def test_registered(self):