[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>

examples/offline_inference/cosyvoice3/README.md

@@ -58,7 +58,14 @@ Key components live in `vllm_omni/model_executor/models/cosyvoice3/cosyvoice3.py
     - Stage 0 uses `CosyVoice3LM` and outputs speech tokens + conditioning features.
     - Stage 1 runs the flow model (DiT-based CFM) and HiFiGAN to synthesize waveform.
 
-Stage wiring is configured in `vllm_omni/model_executor/stage_configs/cosyvoice3.yaml`.
+Pipeline topology lives in `vllm_omni/model_executor/models/cosyvoice3/pipeline.py`;
+runtime tunables (batch size, memory limits, sampling) live in
+`vllm_omni/deploy/cosyvoice3.yaml`. The deploy config auto-loads by
+HF `model_type` and defaults to `async_chunk: true` (shared-memory
+streaming). Pass `--no-async-chunk` on `vllm serve` to switch to the
+legacy sync path where stage 1 runs `text2flow` over the full
+speech-token sequence.
 
 - Stage 0 emits latent speech tokens.
-- Stage 1 consumes them via `custom_process_input_func` and outputs audio.
+- Stage 1 consumes them via `sync_process_input_func` (sync mode) or the
+  shared-memory connector (async-chunk mode) and outputs audio.

examples/offline_inference/cosyvoice3/verify_e2e_cosyvoice.py

@@ -24,7 +24,13 @@ def run_e2e():
         required=True,
         help="Path to CosyVoice3 model directory (e.g., pretrained_models/Fun-CosyVoice3-0.5B/).",
     )
-    parser.add_argument("--stage-config", type=str, default="vllm_omni/model_executor/stage_configs/cosyvoice3.yaml")
+    parser.add_argument(
+        "--deploy-config",
+        type=str,
+        default=None,
+        help="Override the deploy config path. If unset, auto-loads "
+        "vllm_omni/deploy/cosyvoice3.yaml based on the HF model_type.",
+    )
     parser.add_argument("--prompt", type=str, default="Hello, this is a test of the CosyVoice system capability.")
     parser.add_argument(
         "--prompt-text",
@@ -43,18 +49,14 @@ def run_e2e():
     if not os.path.exists(args.tokenizer):
         raise FileNotFoundError(f"{args.tokenizer} does not exist!")
 
-    # Ensure stage config exists
-    if not os.path.exists(args.stage_config):
-        raise FileNotFoundError(f"{args.stage_config} does not exist!")
+    if args.deploy_config is not None and not os.path.exists(args.deploy_config):
+        raise FileNotFoundError(f"{args.deploy_config} does not exist!")
 
     print(f"Initializing cosyvoice E2E with model={args.model}")
 
-    # Initialize Omni
-    # This spins up the engine(s) based on the stage config
-    # We pass trust_remote_code=True same as Qwen examples
     omni = Omni(
         model=args.model,
-        stage_configs_path=args.stage_config,
+        deploy_config=args.deploy_config,
         trust_remote_code=True,
         tokenizer=args.tokenizer,
         log_stats=True,

examples/offline_inference/mimo_audio/README.md

@@ -39,7 +39,6 @@ Run a single sample for basic TTS:
 
 ```bash
 python3 -u end2end.py \
-  --stage-configs-path vllm_omni/model_executor/stage_configs/mimo_audio.yaml \
   --model-name XiaomiMiMo/MiMo-Audio-7B-Instruct \
   --query-type tts_sft
 ```
@@ -48,7 +47,6 @@ Run batch samples for basic TTS:
 
 ```bash
 python3 -u end2end.py \
-  --stage-configs-path vllm_omni/model_executor/stage_configs/mimo_audio.yaml \
   --model-name XiaomiMiMo/MiMo-Audio-7B-Instruct \
   --query-type tts_sft \
   --num-prompts {batch_size}
@@ -66,7 +64,6 @@ Generate speech from text input:
 
 ```bash
 python3 -u end2end.py \
-  --stage-configs-path vllm_omni/model_executor/stage_configs/mimo_audio.yaml \
   --model-name XiaomiMiMo/MiMo-Audio-7B-Instruct \
   --query-type tts_sft \
   --text "The weather is so nice today."
@@ -78,7 +75,6 @@ Generate speech with explicit voice style instructions:
 
 ```bash
 python3 -u end2end.py \
-  --stage-configs-path vllm_omni/model_executor/stage_configs/mimo_audio.yaml \
   --model-name XiaomiMiMo/MiMo-Audio-7B-Instruct \
   --query-type tts_sft_with_instruct \
   --text "The weather is so nice today." \
@@ -91,7 +87,6 @@ Generate speech using an audio reference for voice cloning:
 
 ```bash
 python3 -u end2end.py \
-  --stage-configs-path vllm_omni/model_executor/stage_configs/mimo_audio.yaml \
   --model-name XiaomiMiMo/MiMo-Audio-7B-Instruct \
   --query-type tts_sft_with_audio \
   --text "The weather is so nice today." \
@@ -104,7 +99,6 @@ Generate speech from text containing natural voice descriptions:
 
 ```bash
 python3 -u end2end.py \
-  --stage-configs-path vllm_omni/model_executor/stage_configs/mimo_audio.yaml \
   --model-name XiaomiMiMo/MiMo-Audio-7B-Instruct \
   --query-type tts_sft_with_natural_instruction \
   --text "In a panting young male voice, he said: I can't run anymore, wait for me!"
@@ -116,7 +110,6 @@ Transcribe audio to text:
 
 ```bash
 python3 -u end2end.py \
-  --stage-configs-path vllm_omni/model_executor/stage_configs/mimo_audio.yaml \
   --model-name XiaomiMiMo/MiMo-Audio-7B-Instruct \
   --query-type audio_trancribing_sft \
   --audio-path "./spoken_dialogue_assistant_turn_1.wav"
@@ -128,7 +121,6 @@ Understand and analyze audio content with text queries:
 
 ```bash
 python3 -u end2end.py \
-  --stage-configs-path vllm_omni/model_executor/stage_configs/mimo_audio.yaml \
   --model-name XiaomiMiMo/MiMo-Audio-7B-Instruct \
   --query-type audio_understanding_sft \
   --text "Summarize the audio." \
@@ -141,7 +133,6 @@ Audio understanding with reasoning chain:
 
 ```bash
 python3 -u end2end.py \
-  --stage-configs-path vllm_omni/model_executor/stage_configs/mimo_audio.yaml \
   --model-name XiaomiMiMo/MiMo-Audio-7B-Instruct \
   --query-type audio_understanding_sft_with_thinking \
   --text "Summarize the audio." \
@@ -154,7 +145,6 @@ Multi-turn dialogue with audio input and output:
 
 ```bash
 python3 -u end2end.py \
-  --stage-configs-path vllm_omni/model_executor/stage_configs/mimo_audio.yaml \
   --model-name XiaomiMiMo/MiMo-Audio-7B-Instruct \
   --query-type spoken_dialogue_sft_multiturn \
   --audio-path "./prompt_speech_zh_m.wav"
@@ -168,7 +158,6 @@ Multi-turn dialogue converting speech to text:
 
 ```bash
 python3 -u end2end.py \
-  --stage-configs-path vllm_omni/model_executor/stage_configs/mimo_audio.yaml \
   --model-name XiaomiMiMo/MiMo-Audio-7B-Instruct \
   --query-type speech2text_dialogue_sft_multiturn
 ```
@@ -181,7 +170,6 @@ Multi-turn text-only dialogue:
 
 ```bash
 python3 -u end2end.py \
-  --stage-configs-path vllm_omni/model_executor/stage_configs/mimo_audio.yaml \
   --model-name XiaomiMiMo/MiMo-Audio-7B-Instruct \
   --query-type text_dialogue_sft_multiturn
 ```

examples/offline_inference/mimo_audio/end2end.py

@@ -182,7 +182,7 @@ def main(args):
 
     omni = Omni(
         model=model_name,
-        stage_configs_path=args.stage_configs_path,
+        deploy_config=args.deploy_config,
         log_stats=args.enable_stats,
         log_file=("omni_pipeline.log" if args.enable_stats else None),
         init_sleep_seconds=args.init_sleep_seconds,
@@ -428,10 +428,11 @@ def parse_args():
         help="Sampling rate for audio.",
     )
     parser.add_argument(
-        "--stage-configs-path",
+        "--deploy-config",
         type=str,
-        default="../../../model_executor/stage_configs/mimo_audio.yaml",
-        help="Path to a stage configs file.",
+        default=None,
+        help="Override the deploy config path. If unset, auto-loads "
+        "vllm_omni/deploy/mimo_audio.yaml based on the HF model_type.",
     )
 
     return parser.parse_args()

examples/offline_inference/voxtral_tts/README.md

@@ -10,28 +10,24 @@ When `mistral_common` has `SpeechRequest` support, prompt token IDs are built vi
 ```bash
 # Basic single-prompt with cheerful_female voice preset
 python3 examples/offline_inference/voxtral_tts/end2end.py \
-    --stage-configs-path vllm_omni/model_executor/stage_configs/voxtral_tts.yaml \
     --write-audio --voice cheerful_female \
     --model mistralai/Voxtral-4B-TTS-2603 \
     --text "That eerie silence after the first storm was just the calm before another round of chaos, wasn't it?"
 
 # 32 replicate prompts with cheerful_female voice preset
 python3 examples/offline_inference/voxtral_tts/end2end.py \
-    --stage-configs-path vllm_omni/model_executor/stage_configs/voxtral_tts.yaml \
     --num-prompts 32 --write-audio --voice cheerful_female \
     --model mistralai/Voxtral-4B-TTS-2603 \
     --text "That eerie silence after the first storm was just the calm before another round of chaos, wasn't it?"
 
 # Streaming with neutral_female voice preset
 python3 examples/offline_inference/voxtral_tts/end2end.py \
-    --stage-configs-path vllm_omni/model_executor/stage_configs/voxtral_tts.yaml \
     --streaming --write-audio --voice neutral_female \
     --model mistralai/Voxtral-4B-TTS-2603 \
     --text "That eerie silence after the first storm was just the calm before another round of chaos, wasn't it?"
 
 # 32 prompts, 8 concurrent requests per wave, streaming with neutral_female voice
 python3 examples/offline_inference/voxtral_tts/end2end.py \
-    --stage-configs-path vllm_omni/model_executor/stage_configs/voxtral_tts.yaml \
     --num-prompts 32 --concurrency 8 --streaming --write-audio --voice neutral_female \
     --model mistralai/Voxtral-4B-TTS-2603 \
     --text "That eerie silence after the first storm was just the calm before another round of chaos, wasn't it?"
@@ -39,7 +35,6 @@ python3 examples/offline_inference/voxtral_tts/end2end.py \
 # Short debug prompt with reference audio
 # Note: Reference audio capability is not yet released.
 python3 examples/offline_inference/voxtral_tts/end2end.py \
-    --stage-configs-path vllm_omni/model_executor/stage_configs/voxtral_tts.yaml \
     --write-audio \
     --model mistralai/Voxtral-4B-TTS-2603 \
     --text "This is a test message." \
@@ -54,7 +49,7 @@ python3 examples/offline_inference/voxtral_tts/end2end.py \
 | `--text TEXT` | Text to synthesize (default: `"This is a test message."`) |
 | `--audio-path PATH` | Path to reference audio file for voice cloning |
 | `--output-dir DIR` | Directory to write output WAV files (default: `output_audio`) |
-| `--stage-configs-path PATH` | Path to stage configs YAML (currently it must be set for VoxtralTTS) |
+| `--deploy-config PATH` | Override the deploy config path. If unset, auto-loads `vllm_omni/deploy/voxtral_tts.yaml` from the HF `model_type`. |
 | `--num-prompts N` | Number of replicate prompts to run for measuring performance (default: 1) |
 | `--streaming` | Use streaming generation via `AsyncOmni` (default: blocking `Omni`) |
 | `--concurrency N` | Max concurrent requests per wave (must be used with `--streaming`, must evenly divide `--num-prompts`) |

examples/offline_inference/voxtral_tts/end2end.py

@@ -39,7 +39,7 @@ logger = logging.getLogger(__name__)
 async def run_streaming(inputs, sampling_params_list, model_name, args, output_dir):
     async_omni = AsyncOmni(
         model=model_name,
-        stage_configs_path=args.stage_configs_path,
+        deploy_config=args.deploy_config,
         log_stats=args.log_stats,
     )
 
@@ -192,7 +192,7 @@ def run_non_streaming(inputs, sampling_params_list, model_name, args, output_dir
     llm = Omni(
         model=model_name,
         log_stats=args.log_stats,
-        stage_configs_path=args.stage_configs_path,
+        deploy_config=args.deploy_config,
     )
 
     if args.profiling_mode:
@@ -253,10 +253,11 @@ def parse_args() -> Namespace:
         help="Directory to write output wav files.",
     )
     parser.add_argument(
-        "--stage-configs-path",
+        "--deploy-config",
         type=str,
         default=None,
-        help="Path to stage configs YAML. Auto-resolved from model if not set.",
+        help="Override the deploy config path. If unset, auto-loads "
+        "vllm_omni/deploy/voxtral_tts.yaml based on the HF model_type.",
     )
     parser.add_argument(
         "--num-prompts", type=int, default=1, help="Number of replicate prompts to run for measuring performance"

examples/online_serving/fish_speech/README.md

@@ -29,15 +29,12 @@ Features:
 ## Launch the Server
 
 ```bash
-vllm-omni serve fishaudio/s2-pro \
-    --stage-configs-path vllm_omni/model_executor/stage_configs/fish_speech_s2_pro.yaml \
-    --omni \
-    --port 8091 \
-    --trust-remote-code \
-    --enforce-eager \
-    --gpu-memory-utilization 0.9
+vllm serve fishaudio/s2-pro --omni --port 8091
 ```
 
+The deploy config is auto-loaded from `vllm_omni/deploy/fish_qwen3_omni.yaml`
+(the HF `model_type` on the fishaudio checkpoints is `fish_qwen3_omni`).
+
 Or use the convenience script:
 
 ```bash

examples/online_serving/fish_speech/run_gradio_demo.sh

@@ -11,18 +11,13 @@ MODEL="${MODEL:-fishaudio/s2-pro}"
 PORT="${PORT:-8091}"
 GRADIO_PORT="${GRADIO_PORT:-7860}"
 SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)"
-REPO_ROOT="$(cd "$SCRIPT_DIR/../../.." && pwd)"
 
 echo "Starting Fish Speech S2 Pro server (port $PORT)..."
 FLASHINFER_DISABLE_VERSION_CHECK=1 \
-vllm-omni serve "$MODEL" \
-    --stage-configs-path "$REPO_ROOT/vllm_omni/model_executor/stage_configs/fish_speech_s2_pro.yaml" \
+vllm serve "$MODEL" \
+    --omni \
     --host 0.0.0.0 \
-    --port "$PORT" \
-    --gpu-memory-utilization 0.9 \
-    --trust-remote-code \
-    --enforce-eager \
-    --omni &
+    --port "$PORT" &
 SERVER_PID=$!
 
 cleanup() {

examples/online_serving/fish_speech/run_server.sh

@@ -13,11 +13,7 @@ PORT="${PORT:-8091}"
 echo "Starting Fish Speech S2 Pro server with model: $MODEL"
 
 FLASHINFER_DISABLE_VERSION_CHECK=1 \
-vllm-omni serve "$MODEL" \
-    --stage-configs-path vllm_omni/model_executor/stage_configs/fish_speech_s2_pro.yaml \
+vllm serve "$MODEL" \
+    --omni \
     --host 0.0.0.0 \
-    --port "$PORT" \
-    --gpu-memory-utilization 0.9 \
-    --trust-remote-code \
-    --enforce-eager \
-    --omni
+    --port "$PORT"

examples/online_serving/mimo_audio/README.md

@@ -13,10 +13,10 @@ Please refer to [README.md](../../../README.md)
 ```bash
 export MIMO_AUDIO_TOKENIZER_PATH="XiaomiMiMo/MiMo-Audio-Tokenizer"
 
-vllm-omni serve XiaomiMiMo/MiMo-Audio-7B-Instruct --omni \
---served-model-name "MiMo-Audio-7B-Instruct"  \
---port 18091 --stage-configs-path ./vllm_omni/model_executor/stage_configs/mimo_audio.yaml \
---chat-template ./examples/online_serving/mimo_audio/chat_template.jinja
+vllm serve XiaomiMiMo/MiMo-Audio-7B-Instruct --omni \
+    --served-model-name "MiMo-Audio-7B-Instruct" \
+    --port 18091 \
+    --chat-template ./examples/online_serving/mimo_audio/chat_template.jinja
 ```
 > ⚠️ **Important**  
 > **MiMo-Audio is not compatible with the default chat template.**  

examples/online_serving/voxcpm2/README.md

@@ -5,12 +5,13 @@ Serve VoxCPM2 TTS via the OpenAI-compatible `/v1/audio/speech` endpoint.
 ## Start the Server
 
 ```bash
-python -m vllm_omni.entrypoints.openai.api_server \
-    --model openbmb/VoxCPM2 \
-    --stage-configs-path vllm_omni/model_executor/stage_configs/voxcpm2.yaml \
-    --host 0.0.0.0 --port 8000
+vllm serve openbmb/VoxCPM2 --omni --host 0.0.0.0 --port 8000
 ```
 
+The deploy config is auto-loaded from `vllm_omni/deploy/voxcpm2.yaml`. Pass
+`--deploy-config <path>` to override, or `--stage-N-<field> <value>` (e.g.
+`--stage-0-max-num-seqs 8`) for per-stage runtime overrides.
+
 ## Zero-shot Synthesis
 
 ```bash

examples/online_serving/voxcpm2/gradio_demo.py

@@ -8,10 +8,7 @@ the audio clock rate.
 
 Usage:
     # Start the vLLM server first:
-    python -m vllm_omni.entrypoints.openai.api_server \
-        --model openbmb/VoxCPM2 \
-        --stage-configs-path vllm_omni/model_executor/stage_configs/voxcpm2.yaml \
-        --host 0.0.0.0 --port 8000
+    vllm serve openbmb/VoxCPM2 --omni --host 0.0.0.0 --port 8000
 
     # Then launch the demo:
     python gradio_demo.py --api-base http://localhost:8000

examples/online_serving/voxcpm2/openai_speech_client.py

@@ -13,10 +13,7 @@ Examples:
         --ref-audio "https://example.com/reference.wav"
 
 Server setup:
-    python -m vllm_omni.entrypoints.openai.api_server \
-        --model openbmb/VoxCPM2 \
-        --stage-configs-path vllm_omni/model_executor/stage_configs/voxcpm2.yaml \
-        --host 0.0.0.0 --port 8000
+    vllm serve openbmb/VoxCPM2 --omni --host 0.0.0.0 --port 8000
 """
 
 from __future__ import annotations