[Config Refactor] Migrate 5 TTS models (VoxCPM2 / CosyVoice3 / MiMo Audio / Voxtral TTS / Fish Speech S2 Pro) to Pipeline + Deploy schema (#2958)

Signed-off-by: Yueqian Lin <linyueqian@outlook.com>
Co-authored-by: SYLAR <125541396+lishunyang12@users.noreply.github.com>
This commit is contained in:
Yueqian LinandSYLAR authored and GitHub committed 2026-04-21 21:17:53 +08:00
1 parent c2578f7131
commit 3f504b45d2
47 files changed
+702 -844

No files matched your search

+6 -24
View File
@@ -12,7 +12,7 @@ import pytest
from tests.helpers.mark import hardware_test
from tests.helpers.media import generate_synthetic_audio
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
from vllm_omni.model_executor.model_loader.weight_utils import (
download_weights_from_hf_specific,
)
@@ -26,26 +26,6 @@ os.environ["VLLM_WORKER_MULTIPROC_METHOD"] = "spawn"
models = ["XiaomiMiMo/MiMo-Audio-7B-Instruct"]
def get_chunk_config():
path = modify_stage_config(
str(Path(__file__).parent.parent / "stage_configs" / "mimo_audio_ci.yaml"),
updates={
"async_chunk": True,
"stage_args": {
0: {
"engine_args.custom_process_next_stage_input_func": "vllm_omni.model_executor.stage_input_processors.mimo_audio.llm2code2wav_async_chunk"
},
1: {
"engine_args.max_model_len": 8192,
"engine_args.max_num_batched_tokens": 8192,
},
},
},
deletes={"stage_args": {1: ["custom_process_input_func"]}},
)
return path
def download_tokenizer():
tokenizer_path = os.environ.get("MIMO_AUDIO_TOKENIZER_PATH", MIMO_AUDIO_TOKENIZER_REPO)
if os.path.exists(tokenizer_path):
@@ -59,19 +39,21 @@ def download_tokenizer():
return local_path
# CI stage config for H100 / MI325
# Guard module-level setup so test collection doesn't fail in environments
# where the model cache is read-only or models aren't available.
try:
stage_configs = [get_chunk_config()]
stage_configs = [get_deploy_config_path("mimo_audio.yaml")]
tokenizer_path = download_tokenizer()
os.environ["MIMO_AUDIO_TOKENIZER_PATH"] = tokenizer_path
# --load-format dummy applies to every stage pipeline-wide, avoiding a
# per-stage yaml rewrite (the old approach wrote a tempfile + atexit-unlink
# which raced with CI's process lifecycle).
test_params = [
OmniServerParams(
model=model,
stage_config_path=stage_config,
server_args=["--chat-template", CHAT_TEMPLATE_PATH],
server_args=["--chat-template", CHAT_TEMPLATE_PATH, "--load-format", "dummy"],
)
for model in models
for stage_config in stage_configs