[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/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