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>

examples/offline_inference/moss_tts_nano/README.md

@@ -31,7 +31,7 @@ Options:
   --text-temperature F      Text layer temperature (default: 1.0)
   --batch                   Run a built-in batch of diverse samples (ZH/EN/FR)
   --output-dir DIR          Directory for WAV outputs (default: /tmp/moss_tts_nano_output)
-  --stage-config PATH       Path to stage config YAML
+  --deploy-config PATH      Override deploy YAML (defaults to vllm_omni/deploy/moss_tts_nano.yaml)
   --stage-init-timeout INT  Timeout in seconds for stage init (default: 120)
 ```
 
@@ -77,15 +77,17 @@ python end2end.py --text "Deterministic test." --seed 42
 | `Hina` | JA |
 | `Mei` | JA |
 
-## Stage Config
+## Deploy Config
 
-The stage config is at `vllm_omni/model_executor/stage_configs/moss_tts_nano.yaml`. Key settings:
+Runtime knobs live in `vllm_omni/deploy/moss_tts_nano.yaml` (auto-loaded;
+override with `--deploy-config PATH`). Key stage-level settings:
 
 ```yaml
-engine_args:
-  gpu_memory_utilization: 0.3   # ~2 GB VRAM; increase for faster init
-  max_num_seqs: 4               # concurrent requests
-  max_model_len: 4096
+stages:
+  - stage_id: 0
+    gpu_memory_utilization: 0.3   # ~2 GB VRAM; increase for faster init
+    max_num_seqs: 4               # concurrent requests
+    max_model_len: 4096
 ```
 
 ## Output Format

examples/offline_inference/moss_tts_nano/end2end.py

@@ -39,9 +39,6 @@ from vllm_omni import Omni  # noqa: E402
 
 MODEL = "OpenMOSS-Team/MOSS-TTS-Nano"
 
-_REPO_ROOT = Path(__file__).resolve().parents[4]
-DEFAULT_STAGE_CONFIG = str(_REPO_ROOT / "vllm_omni" / "model_executor" / "stage_configs" / "moss_tts_nano.yaml")
-
 BATCH_SAMPLES = [
     {"text": "Hello, this is a test of MOSS-TTS-Nano.", "voice": "Ava", "label": "en_hello"},
     {"text": "你好，这是 MOSS-TTS-Nano 的语音合成测试。", "voice": "Junhao", "label": "zh_hello"},
@@ -98,7 +95,7 @@ def save_audio(waveform: torch.Tensor, path: str, sample_rate: int = 48000) -> N
 def main(args) -> None:
     omni = Omni(
         model=MODEL,
-        stage_configs_path=args.stage_config,
+        deploy_config=args.deploy_config,
         stage_init_timeout=args.stage_init_timeout,
     )
 
@@ -170,7 +167,11 @@ def parse_args():
     parser.add_argument("--text-temperature", type=float, default=1.0)
     parser.add_argument("--batch", action="store_true", help="Run built-in batch of diverse samples.")
     parser.add_argument("--output-dir", default="/tmp/moss_tts_nano_output", help="Directory for WAV outputs.")
-    parser.add_argument("--stage-config", default=DEFAULT_STAGE_CONFIG)
+    parser.add_argument(
+        "--deploy-config",
+        default=None,
+        help="Path to a deploy YAML; leave unset to auto-load vllm_omni/deploy/moss_tts_nano.yaml.",
+    )
     parser.add_argument("--stage-init-timeout", type=int, default=120)
     return parser.parse_args()
 

examples/online_serving/moss_tts_nano/README.md

@@ -29,14 +29,13 @@ Features:
 ## Launch the Server
 
 ```bash
-vllm-omni serve OpenMOSS-Team/MOSS-TTS-Nano \
-    --stage-configs-path vllm_omni/model_executor/stage_configs/moss_tts_nano.yaml \
-    --omni \
-    --port 8091 \
-    --trust-remote-code \
-    --enforce-eager
+vllm serve OpenMOSS-Team/MOSS-TTS-Nano --omni --port 8091
 ```
 
+The deploy config at `vllm_omni/deploy/moss_tts_nano.yaml` auto-loads; no
+`--stage-configs-path`, `--trust-remote-code`, or `--enforce-eager` flags
+are needed.
+
 Or use the convenience script:
 
 ```bash

examples/online_serving/moss_tts_nano/run_gradio_demo.sh

@@ -11,16 +11,12 @@ MODEL="${MODEL:-OpenMOSS-Team/MOSS-TTS-Nano}"
 PORT="${PORT:-8091}"
 GRADIO_PORT="${GRADIO_PORT:-7860}"
 SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)"
-REPO_ROOT="$(cd "$SCRIPT_DIR/../../.." && pwd)"
 
 echo "Starting MOSS-TTS-Nano server (port $PORT)..."
 FLASHINFER_DISABLE_VERSION_CHECK=1 \
-vllm-omni serve "$MODEL" \
-    --stage-configs-path "$REPO_ROOT/vllm_omni/model_executor/stage_configs/moss_tts_nano.yaml" \
+vllm serve "$MODEL" \
     --host 0.0.0.0 \
     --port "$PORT" \
-    --trust-remote-code \
-    --enforce-eager \
     --omni &
 SERVER_PID=$!
 

examples/online_serving/moss_tts_nano/run_server.sh

@@ -9,16 +9,11 @@ set -e
 
 MODEL="${MODEL:-OpenMOSS-Team/MOSS-TTS-Nano}"
 PORT="${PORT:-8091}"
-SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)"
-REPO_ROOT="$(cd "$SCRIPT_DIR/../../.." && pwd)"
 
 echo "Starting MOSS-TTS-Nano server with model: $MODEL"
 
 FLASHINFER_DISABLE_VERSION_CHECK=1 \
-vllm-omni serve "$MODEL" \
-    --stage-configs-path "$REPO_ROOT/vllm_omni/model_executor/stage_configs/moss_tts_nano.yaml" \
+vllm serve "$MODEL" \
     --host 0.0.0.0 \
     --port "$PORT" \
-    --trust-remote-code \
-    --enforce-eager \
     --omni