[Doc] ruff format remaining Python examples (#26795)

Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>

docs/models/extensions/tensorizer.md

@@ -60,7 +60,7 @@ from vllm import LLM
 llm = LLM(
     "s3://my-bucket/vllm/facebook/opt-125m/v1", 
     load_format="tensorizer",
-    enable_lora=True
+    enable_lora=True,
 )
 ```
 
@@ -97,6 +97,6 @@ llm = LLM(
     "s3://my-bucket/vllm/facebook/opt-125m/v1", 
     load_format="tensorizer",
     enable_lora=True,
-    model_loader_extra_config={"deserialization_kwargs": {"num_readers": 2}}
+    model_loader_extra_config={"deserialization_kwargs": {"num_readers": 2}},
 )
 ```

docs/models/generative_models.md

@@ -98,15 +98,15 @@ and automatically applies the model's [chat template](https://huggingface.co/doc
     conversation = [
         {
             "role": "system",
-            "content": "You are a helpful assistant"
+            "content": "You are a helpful assistant",
         },
         {
             "role": "user",
-            "content": "Hello"
+            "content": "Hello",
         },
         {
             "role": "assistant",
-            "content": "Hello! How can I assist you today?"
+            "content": "Hello! How can I assist you today?",
         },
         {
             "role": "user",

docs/models/pooling_models.md

@@ -130,8 +130,10 @@ It is designed for embedding models and cross-encoder models. Embedding models u
 from vllm import LLM
 
 llm = LLM(model="BAAI/bge-reranker-v2-m3", runner="pooling")
-(output,) = llm.score("What is the capital of France?",
-                      "The capital of Brazil is Brasilia.")
+(output,) = llm.score(
+    "What is the capital of France?",
+    "The capital of Brazil is Brasilia.",
+)
 
 score = output.outputs.score
 print(f"Score: {score}")
@@ -209,7 +211,7 @@ For models that support Matryoshka Embeddings but not recognized by vLLM, please
 
 Here is an example to serve a model with Matryoshka Embeddings enabled.
 
-```text
+```bash
 vllm serve Snowflake/snowflake-arctic-embed-m-v1.5 --hf-overrides '{"matryoshka_dimensions":[256]}'
 ```
 
@@ -220,11 +222,15 @@ You can change the output dimensions of embedding models that support Matryoshka
 ```python
 from vllm import LLM, PoolingParams
 
-llm = LLM(model="jinaai/jina-embeddings-v3",
-          runner="pooling",
-          trust_remote_code=True)
-outputs = llm.embed(["Follow the white rabbit."],
-                    pooling_params=PoolingParams(dimensions=32))
+llm = LLM(
+    model="jinaai/jina-embeddings-v3",
+    runner="pooling",
+    trust_remote_code=True,
+)
+outputs = llm.embed(
+    ["Follow the white rabbit."],
+    pooling_params=PoolingParams(dimensions=32),
+)
 print(outputs[0].outputs)
 ```
 
@@ -234,13 +240,13 @@ A code example can be found here: <gh-file:examples/offline_inference/pooling/em
 
 Use the following command to start vllm server.
 
-```text
+```bash
 vllm serve jinaai/jina-embeddings-v3 --trust-remote-code
 ```
 
 You can change the output dimensions of embedding models that support Matryoshka Embeddings by using the dimensions parameter.
 
-```text
+```bash
 curl http://127.0.0.1:8000/v1/embeddings \
   -H 'accept: application/json' \
   -H 'Content-Type: application/json' \

docs/models/supported_models.md

@@ -278,8 +278,8 @@ https_proxy=http://your.proxy.server:port  vllm serve <model_name>
 ```python
 import os
 
-os.environ['http_proxy'] = 'http://your.proxy.server:port'
-os.environ['https_proxy'] = 'http://your.proxy.server:port'
+os.environ["http_proxy"] = "http://your.proxy.server:port"
+os.environ["https_proxy"] = "http://your.proxy.server:port"
 ```
 
 ### ModelScope