[Refactor] Migrate Legacy Stage Configs to the Pipeline Registry (#5031)

Signed-off-by: zwhzzz0821 <2831474076@qq.com>
Co-authored-by: zwhzzz0821 <zwhzzz0821@users.noreply.github.com>
Co-authored-by: SYLAR <125541396+lishunyang12@users.noreply.github.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>

examples/online_serving/step_audio2/README.md

@@ -10,15 +10,15 @@ Please refer to [README.md](../../../README.md)
 
 ```bash
 # Async chunk mode (recommended — lower first-packet latency for TTS)
-vllm serve stepfun-ai/Step-Audio2-mini --omni --port 8092 \
-    --stage-configs-path vllm_omni/model_executor/stage_configs/step_audio_2_async_chunk.yaml \
+vllm serve stepfun-ai/Step-Audio-2-mini --omni --port 8092 \
+    --deploy-config vllm_omni/deploy/step_audio_2_async_chunk.yaml \
     --trust-remote-code --enforce-eager
 ```
 
 Sequential mode:
 ```bash
-vllm serve stepfun-ai/Step-Audio2-mini --omni --port 8092 \
-    --stage-configs-path vllm_omni/model_executor/stage_configs/step_audio_2.yaml \
+vllm serve stepfun-ai/Step-Audio-2-mini --omni --port 8092 \
+    --deploy-config vllm_omni/deploy/step_audio_2.yaml \
     --trust-remote-code --enforce-eager
 ```
 
@@ -51,7 +51,7 @@ Or via curl:
 ```bash
 curl -X POST http://localhost:8092/v1/audio/speech \
     -H "Content-Type: application/json" \
-    -d '{"model":"stepfun-ai/Step-Audio2-mini","input":"你好世界","voice":"default"}' \
+    -d '{"model":"stepfun-ai/Step-Audio-2-mini","input":"你好世界","voice":"default"}' \
     --output output.wav
 ```
 
@@ -139,7 +139,7 @@ Step-Audio2 uses the OpenAI-compatible chat completions API:
 
 ```json
 {
-  "model": "stepfun-ai/Step-Audio2-mini",
+  "model": "stepfun-ai/Step-Audio-2-mini",
   "messages": [
     {
       "role": "system",

examples/online_serving/step_audio2/openai_chat_completion_client.py

@@ -9,7 +9,7 @@ Step-Audio2 is a two-stage model:
 
 Usage examples:
   # Start server first:
-  vllm serve stepfun-ai/Step-Audio2-mini --omni --port 8092
+  vllm serve stepfun-ai/Step-Audio-2-mini --omni --port 8092
 
   # Audio to text (ASR)
   python openai_chat_completion_client.py --query-type audio_to_text
@@ -311,7 +311,7 @@ def parse_args():
         "--model",
         "-m",
         type=str,
-        default="stepfun-ai/Step-Audio2-mini",
+        default="stepfun-ai/Step-Audio-2-mini",
         help="Model name",
     )
     parser.add_argument(

examples/online_serving/step_audio2/openai_speech_client.py

@@ -87,7 +87,7 @@ def parse_args():
         "--model",
         "-m",
         type=str,
-        default="stepfun-ai/Step-Audio2-mini",
+        default="stepfun-ai/Step-Audio-2-mini",
         help="Model name/path",
     )
     parser.add_argument(

examples/online_serving/step_audio2/run_curl.sh

@@ -110,7 +110,7 @@ output=$(curl -sS -X POST "${API_BASE}/v1/chat/completions" \
     -H "Content-Type: application/json" \
     -d @- <<EOF
 {
-  "model": "stepfun-ai/Step-Audio2-mini",
+  "model": "stepfun-ai/Step-Audio-2-mini",
   "sampling_params_list": $sampling_params_list,
   "messages": [
     {