[Config Refactor] Migrate Ming and Ming-TTS deploy/pipline configs (#3154)

Signed-off-by: Yuanheng Zhao <jonathan.zhaoyh@gmail.com>
Signed-off-by: yuanheng <jonathan.zhaoyh@gmail.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
This commit is contained in:
Yuanheng ZhaoandHongsheng Liu authored and GitHub committed 2026-05-03 14:43:49 +12:00
1 parent 6a837849dd
commit d49356e4ca
25 files changed
+518 -398

No files matched your search

@@ -6,8 +6,6 @@ import os
os.environ["VLLM_WORKER_MULTIPROC_METHOD"] = "spawn"
os.environ["VLLM_TEST_CLEAN_GPU_MEMORY"] = "0"
from pathlib import Path
import pytest
from tests.helpers.mark import hardware_test
@@ -16,7 +14,7 @@ from tests.helpers.media import (
generate_synthetic_image,
generate_synthetic_video,
)
from tests.helpers.stage_config import modify_stage_config
from tests.helpers.stage_config import get_deploy_config_path, modify_stage_config
models = ["Jonathan1909/Ming-flash-omni-2.0"]
@@ -35,48 +33,27 @@ def build_prompt(user_text: str) -> str:
)
_CI_DEPLOY_THINKER_ONLY = get_deploy_config_path("ci/ming_flash_omni_thinker_only.yaml")
_CI_DEPLOY = get_deploy_config_path("ci/ming_flash_omni.yaml")
def get_eager_config_thinker():
return modify_stage_config(_CI_DEPLOY_THINKER_ONLY, updates={"stages": {0: {"enforce_eager": True}}})
def get_eager_config():
path = modify_stage_config(
str(Path(__file__).parent.parent / "stage_configs" / "bailingmm_moe_v2_lite_thinker_only_ci.yaml"),
updates={
"stage_args": {
0: {
"engine_args.enforce_eager": "true",
},
},
},
)
return path
def get_eager_tts_config():
"""Thinker+talker CI config with enforce_eager on the thinker stage."""
path = modify_stage_config(
str(Path(__file__).parent.parent / "stage_configs" / "bailingmm_moe_v2_lite_ci.yaml"),
updates={
"stage_args": {
0: {
"engine_args.enforce_eager": "true",
},
},
},
)
return path
return modify_stage_config(_CI_DEPLOY, updates={"stages": {0: {"enforce_eager": True}}})
# Thinker-only config — used by text-output tests.
stage_configs = [get_eager_config()]
test_params = [(model, stage_config) for model in models for stage_config in stage_configs]
# Thinker+talker config — used by audio-output tests.
stage_configs_tts = [get_eager_tts_config()]
test_params_tts = [(model, stage_config) for model in models for stage_config in stage_configs_tts]
test_params_thinker = [(m, c) for m in models for c in [get_eager_config_thinker()]]
test_params = [(m, c) for m in models for c in [get_eager_config()]]
@pytest.mark.core_model
@pytest.mark.omni
@hardware_test(res={"cuda": "H100"}, num_cards=4)
@pytest.mark.parametrize("omni_runner", test_params, indirect=True)
@pytest.mark.parametrize("omni_runner", test_params_thinker, indirect=True)
def test_text_to_text(omni_runner, omni_runner_handler) -> None:
"""
Test text-only input processing and text output generation.
@@ -92,7 +69,7 @@ def test_text_to_text(omni_runner, omni_runner_handler) -> None:
@pytest.mark.core_model
@pytest.mark.omni
@hardware_test(res={"cuda": "H100"}, num_cards=4)
@pytest.mark.parametrize("omni_runner", test_params, indirect=True)
@pytest.mark.parametrize("omni_runner", test_params_thinker, indirect=True)
def test_image_to_text(omni_runner, omni_runner_handler) -> None:
"""
Test image understanding with text output.
@@ -109,7 +86,7 @@ def test_image_to_text(omni_runner, omni_runner_handler) -> None:
@pytest.mark.core_model
@pytest.mark.omni
@hardware_test(res={"cuda": "H100"}, num_cards=4)
@pytest.mark.parametrize("omni_runner", test_params, indirect=True)
@pytest.mark.parametrize("omni_runner", test_params_thinker, indirect=True)
def test_audio_to_text(omni_runner, omni_runner_handler) -> None:
"""
Test audio understanding with text output.
@@ -128,7 +105,7 @@ def test_audio_to_text(omni_runner, omni_runner_handler) -> None:
@pytest.mark.core_model
@pytest.mark.omni
@hardware_test(res={"cuda": "H100"}, num_cards=4)
@pytest.mark.parametrize("omni_runner", test_params, indirect=True)
@pytest.mark.parametrize("omni_runner", test_params_thinker, indirect=True)
def test_video_to_text(omni_runner, omni_runner_handler) -> None:
"""
Test video understanding with text output.
@@ -145,7 +122,7 @@ def test_video_to_text(omni_runner, omni_runner_handler) -> None:
@pytest.mark.core_model
@pytest.mark.omni
@hardware_test(res={"cuda": "H100"}, num_cards=4)
@pytest.mark.parametrize("omni_runner", test_params, indirect=True)
@pytest.mark.parametrize("omni_runner", test_params_thinker, indirect=True)
def test_mixed_to_text(omni_runner, omni_runner_handler) -> None:
"""
Test mixed modality input (image + audio) with text output.
@@ -165,7 +142,7 @@ def test_mixed_to_text(omni_runner, omni_runner_handler) -> None:
@pytest.mark.advanced_model
@pytest.mark.omni
@hardware_test(res={"cuda": "H100"}, num_cards=4)
@pytest.mark.parametrize("omni_runner", test_params_tts, indirect=True)
@pytest.mark.parametrize("omni_runner", test_params, indirect=True)
def test_text_to_audio(omni_runner, omni_runner_handler) -> None:
"""
Test text input with audio output via the thinker+talker pipeline.
@@ -181,7 +158,7 @@ def test_text_to_audio(omni_runner, omni_runner_handler) -> None:
@pytest.mark.advanced_model
@pytest.mark.omni
@hardware_test(res={"cuda": "H100"}, num_cards=4)
@pytest.mark.parametrize("omni_runner", test_params_tts, indirect=True)
@pytest.mark.parametrize("omni_runner", test_params, indirect=True)
def test_image_to_audio(omni_runner, omni_runner_handler) -> None:
"""
Test image + text input with audio output via the thinker+talker pipeline.
@@ -6,7 +6,6 @@ Tests multimodal understanding via OpenAI-compatible API.
"""
import os
from pathlib import Path
import pytest
@@ -17,29 +16,17 @@ from tests.helpers.media import (
generate_synthetic_video,
)
from tests.helpers.runtime import OmniServerParams, dummy_messages_from_mix_data
from tests.helpers.stage_config import modify_stage_config
from tests.helpers.stage_config import get_deploy_config_path
os.environ["VLLM_WORKER_MULTIPROC_METHOD"] = "spawn"
os.environ["VLLM_TEST_CLEAN_GPU_MEMORY"] = "0"
models = ["Jonathan1909/Ming-flash-omni-2.0"]
# Use thinker-only topology to test text outputs
_CI_DEPLOY = get_deploy_config_path("ci/ming_flash_omni_thinker_only.yaml")
def get_eager_config():
path = modify_stage_config(
str(Path(__file__).parent.parent / "stage_configs" / "bailingmm_moe_v2_lite_ci.yaml"),
updates={
"stage_args": {
0: {
"engine_args.enforce_eager": "true",
},
},
},
)
return path
stage_configs = [get_eager_config()]
stage_configs = [_CI_DEPLOY]
# Create parameter combinations for model and stage config
test_params = [
@@ -1,75 +0,0 @@
# CI stage config for Ming-flash-omni-2.0 thinker+talker pipeline.
# Stage 0: Thinker (multimodal understanding -> text generation)
# Stage 1: Talker (text -> audio waveform via CFM + AudioVAE)
#
# The following config has been verified on 4x H100-80G GPUs
stage_args:
- stage_id: 0
stage_type: llm
runtime:
devices: "0,1,2,3"
max_batch_size: 1
engine_args:
model_stage: thinker
model_arch: MingFlashOmniForConditionalGeneration
worker_type: ar
scheduler_cls: vllm_omni.core.sched.omni_ar_scheduler.OmniARScheduler
gpu_memory_utilization: 0.74
enforce_eager: false
trust_remote_code: true
# Ming Thinker -> talker bridge reads detokenised text from
# source_output.outputs[0].text (not hidden states).
engine_output_type: text
distributed_executor_backend: "mp"
enable_prefix_caching: false
max_num_batched_tokens: 32768
max_model_len: 32768
tensor_parallel_size: 4
hf_config_name: llm_config
load_format: dummy
mm_processor_cache_gb: 0
compilation_config:
pass_config:
# Disable fused all-reduce to avoid a vllm/flashinfer version mismatch.
fuse_allreduce_rms: false
final_output: true
final_output_type: text
is_comprehension: true
default_sampling_params:
temperature: 0.0
top_p: 0.9
max_tokens: 100
repetition_penalty: 1.05
seed: 42
detokenize: true
ignore_eos: false
- stage_id: 1
stage_type: llm
runtime:
devices: "3"
max_batch_size: 1
engine_args:
model_stage: ming_tts
model_arch: MingFlashOmniTalkerForConditionalGeneration
worker_cls: vllm_omni.worker.gpu_generation_worker.GPUGenerationWorker
scheduler_cls: vllm_omni.core.sched.omni_generation_scheduler.OmniGenerationScheduler
gpu_memory_utilization: 0.18
enforce_eager: true
trust_remote_code: true
engine_output_type: audio
enable_prefix_caching: false
max_num_batched_tokens: 1000000
tokenizer_subdir: talker/llm
# The HF repo ships BailingMM2Config (thinker-only) at root;
# OmniModelConfig treats that as "stage does not share outer mrope".
hf_config_name: talker_config
load_format: dummy
engine_input_source: [0]
custom_process_input_func: vllm_omni.model_executor.stage_input_processors.ming_flash_omni.thinker2talker
final_output: true
final_output_type: audio
default_sampling_params:
temperature: 0.0
max_tokens: 1
seed: 42
@@ -1,35 +0,0 @@
# Thinker stage only
stage_args:
- stage_id: 0
stage_type: llm
runtime:
devices: "0,1,2,3"
max_batch_size: 1
engine_args:
model_stage: thinker
model_arch: MingFlashOmniForConditionalGeneration
worker_type: ar
scheduler_cls: vllm_omni.core.sched.omni_ar_scheduler.OmniARScheduler
gpu_memory_utilization: 0.9
enforce_eager: false
trust_remote_code: true
engine_output_type: latent
distributed_executor_backend: "mp"
enable_prefix_caching: false
max_num_batched_tokens: 32768
max_model_len: 32768
tensor_parallel_size: 4
hf_config_name: llm_config
load_format: dummy
mm_processor_cache_gb: 0
final_output: true
final_output_type: text
is_comprehension: true
default_sampling_params:
temperature: 0.4
top_p: 0.9
max_tokens: 100
repetition_penalty: 1.05
seed: 42
detokenize: true
ignore_eos: false