Merge tag 'v0.9.1' into v0.9.1-ori

examples/online_serving/openai_chat_completion_structured_outputs.py

 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 """
 To run this example, you need to start the vLLM server:
 
@@ -138,7 +139,6 @@ def extra_backend_options_completion(client: OpenAI, model: str):
             extra_body={
                 "guided_regex": r"\w+@\w+\.com\n",
                 "stop": ["\n"],
-                "guided_decoding_backend": "xgrammar",
                 "guided_decoding_disable_fallback": True,
             },
         )

examples/online_serving/openai_chat_completion_structured_outputs_structural_tag.py

 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 from openai import OpenAI
 
 # This example demonstrates the `structural_tag` response format.

examples/online_serving/openai_chat_completion_structured_outputs_with_reasoning.py

 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 """
 An example shows how to generate structured outputs from reasoning models
 like DeepSeekR1. The thinking process will not be guided by the JSON

examples/online_serving/openai_chat_completion_tool_calls_with_reasoning.py

 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 """
 An example demonstrates how to use tool calling with reasoning models 
 like QwQ-32B. The reasoning_content will not be parsed by the tool 

examples/online_serving/openai_chat_completion_with_reasoning.py

 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 """
 An example shows how to generate chat completions from reasoning models
 like DeepSeekR1.

examples/online_serving/openai_chat_completion_with_reasoning_streaming.py

 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 """
 An example shows how to generate chat completions from reasoning models
 like DeepSeekR1.

examples/online_serving/openai_chat_embedding_client_for_multimodal.py

 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 
 import argparse
 import base64

examples/online_serving/openai_classification_client.py

 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 
 import argparse
 import pprint

examples/online_serving/openai_completion_client.py

 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 
 import argparse
 

examples/online_serving/openai_cross_encoder_score.py

 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 """
 Example online usage of Score API.
 

examples/online_serving/openai_embedding_client.py

 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 
 from openai import OpenAI
 

examples/online_serving/openai_embedding_matryoshka_fy.py

 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 """Example Python client for embedding API dimensions using vLLM API server
 NOTE:
     start a supported Matryoshka Embeddings model server with `vllm serve`, e.g.

examples/online_serving/openai_pooling_client.py

 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 """
 Example online usage of Pooling API.
 

examples/online_serving/openai_transcription_client.py

 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 import asyncio
 import json
 

examples/online_serving/opentelemetry/dummy_client.py

 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 
 import requests
 from opentelemetry.exporter.otlp.proto.grpc.trace_exporter import OTLPSpanExporter

examples/online_serving/prometheus_grafana/grafana.json

@@ -577,23 +577,6 @@
           "refId": "A",
           "useBackend": false
         },
-        {
-          "datasource": {
-            "type": "prometheus",
-            "uid": "${DS_PROMETHEUS}"
-          },
-          "disableTextWrap": false,
-          "editorMode": "builder",
-          "expr": "vllm:num_requests_swapped{model_name=\"$model_name\"}",
-          "fullMetaSearch": false,
-          "hide": false,
-          "includeNullMetadata": true,
-          "instant": false,
-          "legendFormat": "Num Swapped",
-          "range": true,
-          "refId": "B",
-          "useBackend": false
-        },
         {
           "datasource": {
             "type": "prometheus",
@@ -874,19 +857,6 @@
           "legendFormat": "GPU Cache Usage",
           "range": true,
           "refId": "A"
-        },
-        {
-          "datasource": {
-            "type": "prometheus",
-            "uid": "${DS_PROMETHEUS}"
-          },
-          "editorMode": "code",
-          "expr": "vllm:cpu_cache_usage_perc{model_name=\"$model_name\"}",
-          "hide": false,
-          "instant": false,
-          "legendFormat": "CPU Cache Usage",
-          "range": true,
-          "refId": "B"
         }
       ],
       "title": "Cache Utilization",

examples/online_serving/prompt_embed_inference_with_openai_client.py

 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 """
 vLLM OpenAI-Compatible Client with Prompt Embeddings
 

examples/online_serving/ray_serve_deepseek.py

 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 """
 Example to deploy DeepSeek R1 or V3 with Ray Serve LLM.
 See more details at:

examples/online_serving/retrieval_augmented_generation_with_langchain.py

 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 """
 Retrieval Augmented Generation (RAG) Implementation with Langchain
 ==================================================================

examples/online_serving/retrieval_augmented_generation_with_llamaindex.py

 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 """
 RAG (Retrieval Augmented Generation) Implementation with LlamaIndex
 ================================================================