fix: add missing v1 prefix (#302)

Signed-off-by: Xunzhuo <[email protected]>

Author: Xunzhuo

docs/source/getting_started/examples.rst

@@ -103,7 +103,7 @@ Test the stack's OpenAI-compatible API by querying the available models:
 
 .. code-block:: bash
 
-    curl -o- http://localhost:30080/models
+    curl -o- http://localhost:30080/v1/models
 
 
 Expected output:
@@ -132,7 +132,7 @@ Send a query to the OpenAI `/completion` endpoint to generate a completion for a
 
 .. code-block:: bash
 
-    curl -X POST http://localhost:30080/completions \
+    curl -X POST http://localhost:30080/v1/completions \
       -H "Content-Type: application/json" \
       -d '{
         "model": "facebook/opt-125m",

docs/source/tutorials/kv_cache.rst

@@ -103,7 +103,7 @@ Look for the following log message to confirm LMCache is active:
 
 .. code-block:: bash
 
-    curl -X POST http://localhost:30080/completions \
+    curl -X POST http://localhost:30080/v1/completions \
         -H "Content-Type: application/json" \
         -d '{
             "model": "mistralai/Mistral-7B-Instruct-v0.2",

tutorials/04-launch-multiple-model.md

@@ -95,7 +95,7 @@ helm install vllm vllm/vllm-stack -f tutorials/assets/values-04-multiple-models.
 3. Query the `/models` endpoint to verify the models:
 
    ```bash
-   curl http://localhost:30080/models
+   curl http://localhost:30080/v1/models
    ```
 
    For details on the `/models` endpoint, refer to the [README.md](README.md).

tutorials/05-offload-kv-cache.md

@@ -91,7 +91,7 @@ helm install vllm vllm/vllm-stack -f tutorials/assets/values-05-cpu-offloading.y
 3. Send a request to the stack and observe the logs:
 
    ```bash
-   curl -X POST http://localhost:30080/completions \
+   curl -X POST http://localhost:30080/v1/completions \
      -H "Content-Type: application/json" \
      -d '{
        "model": "mistralai/Mistral-7B-Instruct-v0.2",