docs: standardize API example ports

Signed-off-by: Hongsheng Liu <liuhongsheng4@huawei.com>

docs/serving/README.md

@@ -17,7 +17,7 @@ may also expose standard routes inherited from vLLM, such as
 Start a model with the shared serving command:
 
 ```bash
-vllm serve <model> --omni --port 8000
+vllm serve <model> --omni --port 8091
 ```
 
 Some models require additional flags or a deployment configuration. Use the
@@ -26,13 +26,13 @@ model-specific guide when one is provided.
 After the server starts, check its health and served model name:
 
 ```bash
-export VLLM_OMNI_BASE_URL=http://localhost:8000
+export VLLM_OMNI_BASE_URL=http://localhost:8091
 
 curl "$VLLM_OMNI_BASE_URL/health"
 curl "$VLLM_OMNI_BASE_URL/v1/models" | jq .
 ```
 
-Use `http://localhost:8000/v1` as the `base_url` for an OpenAI SDK client. If
+Use `http://localhost:8091/v1` as the `base_url` for an OpenAI SDK client. If
 the server was started with `--api-key`, include an `Authorization` header with
 `Bearer <api-key>` in requests.
 

docs/serving/full_duplex_api.md

@@ -55,14 +55,14 @@ Start the duplex deployment:
 vllm serve openbmb/MiniCPM-o-4_5 --omni \
   --deploy-config vllm_omni/deploy/minicpmo_4_5_duplex.yaml \
   --trust-remote-code \
-  --port 8099
+  --port 8091
 ```
 
 Stream a mono, PCM16, 16 kHz WAV file with the provided client:
 
 ```bash
 python examples/online_serving/minicpmo/realtime_duplex_demo.py \
-  --url 'ws://localhost:8099/v1/realtime?duplex=1' \
+  --url 'ws://localhost:8091/v1/realtime?duplex=1' \
   --model openbmb/MiniCPM-o-4_5 \
   --input-wav input_16k_mono.wav \
   --ref-audio reference_voice.wav \

docs/serving/openpi_api.md

@@ -33,7 +33,7 @@ and closes.
 Start the bundled DreamZero deployment:
 
 ```bash
-vllm serve GEAR-Dreams/DreamZero-DROID --omni --port 8000 \
+vllm serve GEAR-Dreams/DreamZero-DROID --omni --port 8091 \
   --served-model-name dreamzero-droid \
   --deploy-config vllm_omni/deploy/dreamzero_tp1_cfg2.yaml \
   --enforce-eager --disable-log-stats
@@ -51,7 +51,7 @@ hf download YangshenDeng/vllm-omni-dreamzero-assets \
 
 python examples/online_serving/dreamzero/openpi_client.py \
   --host 127.0.0.1 \
-  --port 8000 \
+  --port 8091 \
   --video-dir outputs/dreamzero/assets
 ```
 

docs/serving/standalone_servers.md

@@ -21,7 +21,7 @@ Start it with:
 ```bash
 HF_TOKEN=... CUDA_VISIBLE_DEVICES=0 python -m \
   vllm_omni.experimental.fullduplex.personaplex.serving.server \
-  --port 8124
+  --port 8091
 ```
 
 | Route | Purpose |
@@ -68,14 +68,14 @@ Start the model backend and orchestrator separately:
 ```bash
 vllm serve jdopensource/JoyAI-VL-Interaction-Preview \
   --served-model-name JoyAI-VL-Interaction-Preview \
-  --port 8061 \
+  --port 8092 \
   --max-model-len 131072 \
   --enable-prefix-caching \
   --limit-mm-per-prompt '{"image":256,"video":1}'
 
 python -m vllm_omni.experimental.fullduplex.joyvl.serving.server \
-  --port 8070 \
-  --main-backend-url http://127.0.0.1:8061/v1 \
+  --port 8091 \
+  --main-backend-url http://127.0.0.1:8092/v1 \
   --main-model JoyAI-VL-Interaction-Preview
 ```
 
@@ -94,7 +94,7 @@ include an `interaction` block whose action is `silence`, `response`, or
 `delegate`.
 
 ```bash
-curl http://127.0.0.1:8070/v1/chat/completions \
+curl http://127.0.0.1:8091/v1/chat/completions \
   -H 'content-type: application/json' \
   -H 'x-session-id: demo' \
   -d '{

docs/serving/streaming_video_output_api.md

@@ -13,7 +13,7 @@ output:
 ```bash
 vllm serve BestWishYsh/Helios-Distilled --omni \
   --diffusion-streaming-output \
-  --port 8000
+  --port 8091
 ```
 
 Install the client dependency and run the provided client:
@@ -23,7 +23,7 @@ pip install websockets
 
 python examples/online_serving/streaming_video_generation/streaming_video_client.py \
   --host 127.0.0.1 \
-  --port 8000 \
+  --port 8091 \
   --model BestWishYsh/Helios-Distilled \
   --prompt "A serene lakeside sunrise with mist over the water" \
   --output output.mp4