[Quality] Add code formatter and linter (#326)

examples/api_client.py

@@ -14,7 +14,9 @@ def clear_line(n: int = 1) -> None:
         print(LINE_UP, end=LINE_CLEAR, flush=True)
 
 
-def post_http_request(prompt: str, api_url: str, n: int = 1,
+def post_http_request(prompt: str,
+                      api_url: str,
+                      n: int = 1,
                       stream: bool = False) -> requests.Response:
     headers = {"User-Agent": "Test Client"}
     pload = {
@@ -30,7 +32,8 @@ def post_http_request(prompt: str, api_url: str, n: int = 1,
 
 
 def get_streaming_response(response: requests.Response) -> Iterable[List[str]]:
-    for chunk in response.iter_lines(chunk_size=8192, decode_unicode=False,
+    for chunk in response.iter_lines(chunk_size=8192,
+                                     decode_unicode=False,
                                      delimiter=b"\0"):
         if chunk:
             data = json.loads(chunk.decode("utf-8"))

examples/gradio_webserver.py

@@ -12,9 +12,14 @@ def http_bot(prompt):
         "stream": True,
         "max_tokens": 128,
     }
-    response = requests.post(args.model_url, headers=headers, json=pload, stream=True)
+    response = requests.post(args.model_url,
+                             headers=headers,
+                             json=pload,
+                             stream=True)
 
-    for chunk in response.iter_lines(chunk_size=8192, decode_unicode=False, delimiter=b"\0"):
+    for chunk in response.iter_lines(chunk_size=8192,
+                                     decode_unicode=False,
+                                     delimiter=b"\0"):
         if chunk:
             data = json.loads(chunk.decode("utf-8"))
             output = data["text"][0]
@@ -23,11 +28,11 @@ def http_bot(prompt):
 
 def build_demo():
     with gr.Blocks() as demo:
-        gr.Markdown(
-            "# vLLM text completion demo\n"
-        )
-        inputbox = gr.Textbox(label="Input", placeholder="Enter text and press ENTER")
-        outputbox = gr.Textbox(label="Output", placeholder="Generated result from the model")
+        gr.Markdown("# vLLM text completion demo\n")
+        inputbox = gr.Textbox(label="Input",
+                              placeholder="Enter text and press ENTER")
+        outputbox = gr.Textbox(label="Output",
+                               placeholder="Generated result from the model")
         inputbox.submit(http_bot, [inputbox], [outputbox])
     return demo
 
@@ -36,7 +41,9 @@ if __name__ == "__main__":
     parser = argparse.ArgumentParser()
     parser.add_argument("--host", type=str, default="localhost")
     parser.add_argument("--port", type=int, default=8001)
-    parser.add_argument("--model-url", type=str, default="http://localhost:8000/generate")
+    parser.add_argument("--model-url",
+                        type=str,
+                        default="http://localhost:8000/generate")
     args = parser.parse_args()
 
     demo = build_demo()

examples/llm_engine_example.py

@@ -14,9 +14,14 @@ def main(args: argparse.Namespace):
         ("To be or not to be,",
          SamplingParams(temperature=0.8, top_k=5, presence_penalty=0.2)),
         ("What is the meaning of life?",
-         SamplingParams(n=2, best_of=5, temperature=0.8, top_p=0.95, frequency_penalty=0.1)),
+         SamplingParams(n=2,
+                        best_of=5,
+                        temperature=0.8,
+                        top_p=0.95,
+                        frequency_penalty=0.1)),
         ("It is only with the heart that one can see rightly",
-         SamplingParams(n=3, best_of=3, use_beam_search=True, temperature=0.0)),
+         SamplingParams(n=3, best_of=3, use_beam_search=True,
+                        temperature=0.0)),
     ]
 
     # Run the engine by calling `engine.step()` manually.

examples/offline_inference.py

@@ -1,6 +1,5 @@
 from vllm import LLM, SamplingParams
 
-
 # Sample prompts.
 prompts = [
     "Hello, my name is",

examples/openai_client.py

@@ -12,8 +12,13 @@ print("Models:", models)
 # Test completion API
 stream = True
 completion = openai.Completion.create(
-    model=model, prompt="A robot may not injure a human being", echo=False, n=2,
-    best_of=3, stream=stream, logprobs=3)
+    model=model,
+    prompt="A robot may not injure a human being",
+    echo=False,
+    n=2,
+    best_of=3,
+    stream=stream,
+    logprobs=3)
 
 # print the completion
 if stream: