Convert `examples` to `ruff-format` (#18400)

Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>

examples/offline_inference/torchrun_example.py

@@ -45,8 +45,7 @@ if dist.get_rank() == 0:
     for output in outputs:
         prompt = output.prompt
         generated_text = output.outputs[0].text
-        print(f"Prompt: {prompt!r}\n"
-              f"Generated text: {generated_text!r}\n")
+        print(f"Prompt: {prompt!r}\nGenerated text: {generated_text!r}\n")
         print("-" * 50)
     """
 Further tips:

examples/offline_inference/tpu.py

@@ -20,10 +20,12 @@ sampling_params = SamplingParams(temperature=0, top_p=1.0, n=N, max_tokens=16)
 def main():
     # Set `enforce_eager=True` to avoid ahead-of-time compilation.
     # In real workloads, `enforace_eager` should be `False`.
-    llm = LLM(model="Qwen/Qwen2-1.5B-Instruct",
-              max_num_batched_tokens=64,
-              max_num_seqs=4,
-              max_model_len=128)
+    llm = LLM(
+        model="Qwen/Qwen2-1.5B-Instruct",
+        max_num_batched_tokens=64,
+        max_num_seqs=4,
+        max_model_len=128,
+    )
     outputs = llm.generate(prompts, sampling_params)
     print("-" * 50)
     for output, answer in zip(outputs, answers):

examples/offline_inference/vision_language_embedding.py

@@ -6,6 +6,7 @@ the correct prompt format on vision language models for multimodal embedding.
 For most models, the prompt format should follow corresponding examples
 on HuggingFace model repository.
 """
+
 from argparse import Namespace
 from dataclasses import asdict
 from typing import Literal, NamedTuple, Optional, TypedDict, Union, get_args
@@ -44,19 +45,17 @@ class ModelRequestData(NamedTuple):
 
 
 def run_e5_v(query: Query) -> ModelRequestData:
-    llama3_template = '<|start_header_id|>user<|end_header_id|>\n\n{}<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n \n'  # noqa: E501
+    llama3_template = "<|start_header_id|>user<|end_header_id|>\n\n{}<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n \n"  # noqa: E501
 
     if query["modality"] == "text":
         text = query["text"]
-        prompt = llama3_template.format(
-            f"{text}\nSummary above sentence in one word: ")
+        prompt = llama3_template.format(f"{text}\nSummary above sentence in one word: ")
         image = None
     elif query["modality"] == "image":
-        prompt = llama3_template.format(
-            "<image>\nSummary above image in one word: ")
+        prompt = llama3_template.format("<image>\nSummary above image in one word: ")
         image = query["image"]
     else:
-        modality = query['modality']
+        modality = query["modality"]
         raise ValueError(f"Unsupported query modality: '{modality}'")
 
     engine_args = EngineArgs(
@@ -83,10 +82,12 @@ def run_vlm2vec(query: Query) -> ModelRequestData:
         image = query["image"]
     elif query["modality"] == "text+image":
         text = query["text"]
-        prompt = f"<|image_1|> Represent the given image with the following question: {text}"  # noqa: E501
+        prompt = (
+            f"<|image_1|> Represent the given image with the following question: {text}"  # noqa: E501
+        )
         image = query["image"]
     else:
-        modality = query['modality']
+        modality = query["modality"]
         raise ValueError(f"Unsupported query modality: '{modality}'")
 
     engine_args = EngineArgs(
@@ -136,7 +137,8 @@ def run_encode(model: str, modality: QueryModality, seed: Optional[int]):
     # Disable other modalities to save memory
     default_limits = {"image": 0, "video": 0, "audio": 0}
     req_data.engine_args.limit_mm_per_prompt = default_limits | dict(
-        req_data.engine_args.limit_mm_per_prompt or {})
+        req_data.engine_args.limit_mm_per_prompt or {}
+    )
 
     engine_args = asdict(req_data.engine_args) | {"seed": seed}
     llm = LLM(**engine_args)
@@ -145,10 +147,12 @@ def run_encode(model: str, modality: QueryModality, seed: Optional[int]):
     if req_data.image is not None:
         mm_data["image"] = req_data.image
 
-    outputs = llm.embed({
-        "prompt": req_data.prompt,
-        "multi_modal_data": mm_data,
-    })
+    outputs = llm.embed(
+        {
+            "prompt": req_data.prompt,
+            "multi_modal_data": mm_data,
+        }
+    )
 
     print("-" * 50)
     for output in outputs:
@@ -164,23 +168,30 @@ model_example_map = {
 
 def parse_args():
     parser = FlexibleArgumentParser(
-        description='Demo on using vLLM for offline inference with '
-        'vision language models for multimodal embedding')
-    parser.add_argument('--model-name',
-                        '-m',
-                        type=str,
-                        default="vlm2vec",
-                        choices=model_example_map.keys(),
-                        help='The name of the embedding model.')
-    parser.add_argument('--modality',
-                        type=str,
-                        default="image",
-                        choices=get_args(QueryModality),
-                        help='Modality of the input.')
-    parser.add_argument("--seed",
-                        type=int,
-                        default=None,
-                        help="Set the seed when initializing `vllm.LLM`.")
+        description="Demo on using vLLM for offline inference with "
+        "vision language models for multimodal embedding"
+    )
+    parser.add_argument(
+        "--model-name",
+        "-m",
+        type=str,
+        default="vlm2vec",
+        choices=model_example_map.keys(),
+        help="The name of the embedding model.",
+    )
+    parser.add_argument(
+        "--modality",
+        type=str,
+        default="image",
+        choices=get_args(QueryModality),
+        help="Modality of the input.",
+    )
+    parser.add_argument(
+        "--seed",
+        type=int,
+        default=None,
+        help="Set the seed when initializing `vllm.LLM`.",
+    )
     return parser.parse_args()
 
 

examples/online_serving/api_client.py

@@ -17,16 +17,15 @@ import requests
 
 
 def clear_line(n: int = 1) -> None:
-    LINE_UP = '\033[1A'
-    LINE_CLEAR = '\x1b[2K'
+    LINE_UP = "\033[1A"
+    LINE_CLEAR = "\x1b[2K"
     for _ in range(n):
         print(LINE_UP, end=LINE_CLEAR, flush=True)
 
 
-def post_http_request(prompt: str,
-                      api_url: str,
-                      n: int = 1,
-                      stream: bool = False) -> requests.Response:
+def post_http_request(
+    prompt: str, api_url: str, n: int = 1, stream: bool = False
+) -> requests.Response:
     headers = {"User-Agent": "Test Client"}
     pload = {
         "prompt": prompt,
@@ -35,17 +34,14 @@ def post_http_request(prompt: str,
         "max_tokens": 16,
         "stream": stream,
     }
-    response = requests.post(api_url,
-                             headers=headers,
-                             json=pload,
-                             stream=stream)
+    response = requests.post(api_url, headers=headers, json=pload, stream=stream)
     return response
 
 
 def get_streaming_response(response: requests.Response) -> Iterable[list[str]]:
-    for chunk in response.iter_lines(chunk_size=8192,
-                                     decode_unicode=False,
-                                     delimiter=b"\n"):
+    for chunk in response.iter_lines(
+        chunk_size=8192, decode_unicode=False, delimiter=b"\n"
+    ):
         if chunk:
             data = json.loads(chunk.decode("utf-8"))
             output = data["text"]

examples/online_serving/cohere_rerank_client.py

@@ -6,6 +6,7 @@ Note that `pip install cohere` is needed to run this example.
 
 run: vllm serve BAAI/bge-reranker-base
 """
+
 from typing import Union
 
 import cohere
@@ -16,28 +17,28 @@ model = "BAAI/bge-reranker-base"
 query = "What is the capital of France?"
 
 documents = [
-    "The capital of France is Paris", "Reranking is fun!",
-    "vLLM is an open-source framework for fast AI serving"
+    "The capital of France is Paris",
+    "Reranking is fun!",
+    "vLLM is an open-source framework for fast AI serving",
 ]
 
 
-def cohere_rerank(client: Union[Client, ClientV2], model: str, query: str,
-                  documents: list[str]) -> dict:
+def cohere_rerank(
+    client: Union[Client, ClientV2], model: str, query: str, documents: list[str]
+) -> dict:
     return client.rerank(model=model, query=query, documents=documents)
 
 
 def main():
     # cohere v1 client
-    cohere_v1 = cohere.Client(base_url="http://localhost:8000",
-                              api_key="sk-fake-key")
+    cohere_v1 = cohere.Client(base_url="http://localhost:8000", api_key="sk-fake-key")
     rerank_v1_result = cohere_rerank(cohere_v1, model, query, documents)
     print("-" * 50)
     print("rerank_v1_result:\n", rerank_v1_result)
     print("-" * 50)
 
     # or the v2
-    cohere_v2 = cohere.ClientV2("sk-fake-key",
-                                base_url="http://localhost:8000")
+    cohere_v2 = cohere.ClientV2("sk-fake-key", base_url="http://localhost:8000")
     rerank_v2_result = cohere_rerank(cohere_v2, model, query, documents)
     print("rerank_v2_result:\n", rerank_v2_result)
     print("-" * 50)