refactor(moss_tts_nano): migrate to Pipeline + Deploy schema

Follow-up to #2958. MOSS-TTS-Nano was authored before the schema refactor
and still shipped as a legacy stage_configs yaml; this aligns it with the
same layout the 5 migrated TTS models now use.

- vllm_omni/model_executor/models/moss_tts_nano/pipeline.py declares
  MOSS_TTS_NANO_PIPELINE (single LLM_AR stage, owns_tokenizer, audio
  output, stop_token_ids=[2] as a hard EOS backstop).
- vllm_omni/deploy/moss_tts_nano.yaml holds runtime knobs (max_num_seqs,
  gpu_memory_utilization, enforce_eager, default_sampling_params,
  skip_mm_profiling); trust_remote_code stays at deploy top-level.
- vllm_omni/config/pipeline_registry.py registers the entry so the lazy
  registry can resolve it.
- moss_tts_nano/__init__.py exports MossTTSNanoForGeneration (VoxCPM2 pattern).
- Removed vllm_omni/model_executor/stage_configs/moss_tts_nano.yaml.

Examples, shell scripts, READMEs, and buildkite-invoked tests are
updated to use `vllm serve <model> --omni` / `--deploy-config`
(auto-load kicks in; no --stage-configs-path or --trust-remote-code).

Signed-off-by: Yueqian Lin <linyueqian@outlook.com>

tests/e2e/offline_inference/test_moss_tts_nano.py

@@ -12,7 +12,6 @@ from tests.utils import hardware_test
 from vllm_omni import Omni
 
 MODEL_NAME = "OpenMOSS-Team/MOSS-TTS-Nano"
-STAGE_CONFIG = "vllm_omni/model_executor/stage_configs/moss_tts_nano.yaml"
 SAMPLE_RATE = 48000
 
 DEFAULT_SAMPLING = SamplingParams(
@@ -61,7 +60,7 @@ def _collect_audio(omni: Omni, request: dict) -> tuple[torch.Tensor, int]:
 @pytest.fixture(scope="module")
 def omni_engine():
     """Module-scoped Omni engine to avoid re-loading the model for each test."""
-    return Omni(model=MODEL_NAME, stage_configs_path=STAGE_CONFIG, stage_init_timeout=180)
+    return Omni(model=MODEL_NAME, stage_init_timeout=180)
 
 
 @pytest.mark.omni

tests/e2e/online_serving/test_moss_tts_nano.py

@@ -12,21 +12,15 @@ 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.conftest import OmniServerParams
+from tests.helpers.stage_config import get_deploy_config_path
 from tests.utils import hardware_test
 
 MODEL = "OpenMOSS-Team/MOSS-TTS-Nano"
 
 
-def get_stage_config(name: str = "moss_tts_nano.yaml"):
-    """Get the stage config path from vllm_omni model_executor stage_configs."""
-    return str(Path(__file__).parent.parent.parent.parent / "vllm_omni" / "model_executor" / "stage_configs" / name)
-
-
 def get_prompt(prompt_type="text"):
     """Text prompt for text-to-audio tests."""
     prompts = {
@@ -40,8 +34,8 @@ tts_server_params = [
     pytest.param(
         OmniServerParams(
             model=MODEL,
-            stage_config_path=get_stage_config("moss_tts_nano.yaml"),
-            server_args=["--trust-remote-code", "--enforce-eager", "--disable-log-stats"],
+            stage_config_path=get_deploy_config_path("moss_tts_nano.yaml"),
+            server_args=["--disable-log-stats"],
         ),
         id="moss_tts_nano",
     )