add precommit

examples/basic/api_client.py

@@ -6,9 +6,9 @@ This example shows how to interact with the vLLM-omni API server
 using HTTP requests.
 """
 
-import requests
 import json
-import time
+
+import requests
 
 
 def test_health(host="localhost", port=8000):
@@ -30,7 +30,7 @@ def test_health(host="localhost", port=8000):
 def generate_text(prompt, host="localhost", port=8000, **kwargs):
     """Generate text using the API server."""
     url = f"http://{host}:{port}/generate"
-    
+
     # Default parameters
     params = {
         "prompts": [prompt],
@@ -40,11 +40,11 @@ def generate_text(prompt, host="localhost", port=8000, **kwargs):
         "frequency_penalty": kwargs.get("frequency_penalty", 0.0),
         "presence_penalty": kwargs.get("presence_penalty", 0.0),
     }
-    
+
     # Add optional parameters
     if "stop" in kwargs:
         params["stop"] = kwargs["stop"]
-    
+
     try:
         response = requests.post(url, json=params, timeout=30)
         response.raise_for_status()
@@ -58,71 +58,64 @@ def main():
     """Main example function."""
     print("vLLM-omni API Client Example")
     print("=" * 40)
-    
+
     # Test server health
     if not test_health():
         print("Please start the server first:")
         print("  vllm serve Qwen/Qwen3-0.6B --omni --port 8000")
         return
-    
+
     # Example 1: Simple generation
     print("\n1. Simple text generation:")
     result = generate_text("Hello, how are you?", max_tokens=50)
     if result:
         text = result["outputs"][0]["text"]
-        print(f"   Input: Hello, how are you?")
+        print("   Input: Hello, how are you?")
         print(f"   Output: {text}")
-    
+
     # Example 2: Creative writing
     print("\n2. Creative writing:")
     result = generate_text(
         "Write a short story about a robot learning to paint",
         max_tokens=150,
-        temperature=0.9
+        temperature=0.9,
     )
     if result:
         text = result["outputs"][0]["text"]
-        print(f"   Input: Write a short story about a robot learning to paint")
+        print("   Input: Write a short story about a robot learning to paint")
         print(f"   Output: {text}")
-    
+
     # Example 3: Question answering
     print("\n3. Question answering:")
     result = generate_text(
-        "What is the capital of France?",
-        max_tokens=30,
-        temperature=0.3
+        "What is the capital of France?", max_tokens=30, temperature=0.3
     )
     if result:
         text = result["outputs"][0]["text"]
-        print(f"   Input: What is the capital of France?")
+        print("   Input: What is the capital of France?")
         print(f"   Output: {text}")
-    
+
     # Example 4: Multiple prompts
     print("\n4. Multiple prompts:")
-    prompts = [
-        "Tell me a joke",
-        "What's 2+2?",
-        "Describe the color blue"
-    ]
-    
+    prompts = ["Tell me a joke", "What's 2+2?", "Describe the color blue"]
+
     for prompt in prompts:
         result = generate_text(prompt, max_tokens=30)
         if result:
             text = result["outputs"][0]["text"]
             print(f"   Q: {prompt}")
             print(f"   A: {text}")
-    
+
     # Example 5: Show full response structure
     print("\n5. Full response structure:")
     result = generate_text("Hello world", max_tokens=20)
     if result:
         print("   Full API response:")
         print(json.dumps(result, indent=2))
-    
+
     print("\n" + "=" * 40)
     print("API client examples completed!")
 
 
 if __name__ == "__main__":
     main()
-

examples/basic/text_generation.py

@@ -7,40 +7,43 @@ with a single AR (Autoregressive) stage.
 """
 
 import asyncio
-from vllm_omni.entrypoints.omni_llm import OmniLLM, AsyncOmniLLM
+
 from vllm_omni.config import create_ar_stage_config
+from vllm_omni.entrypoints.omni_llm import AsyncOmniLLM, OmniLLM
 
 
 def sync_example():
     """Synchronous usage example."""
     print("=== Synchronous vLLM-omni Example ===")
-    
+
     # Create a simple AR stage configuration
     stage_config = create_ar_stage_config(
         stage_id=0,
         model_path="Qwen/Qwen3-0.6B",
         input_modalities=["text"],
-        output_modalities=["text"]
+        output_modalities=["text"],
     )
-    
+
     # Initialize OmniLLM
     omni_llm = OmniLLM([stage_config])
-    
+
     # Prepare stage arguments
-    stage_args = [{
-        "prompt": "Hello, how are you today?",
-        "max_tokens": 50,
-        "temperature": 0.7
-    }]
-    
+    stage_args = [
+        {
+            "prompt": "Hello, how are you today?",
+            "max_tokens": 50,
+            "temperature": 0.7,
+        }
+    ]
+
     # Generate text
     print(f"Input: {stage_args[0]['prompt']}")
     outputs = omni_llm.generate(stage_args)
-    
+
     # Display results
     for i, output in enumerate(outputs):
         print(f"Output {i}:")
-        if hasattr(output, 'outputs') and output.outputs:
+        if hasattr(output, "outputs") and output.outputs:
             for completion in output.outputs:
                 print(f"  Text: {completion.text}")
                 print(f"  Finished: {completion.finish_reason != 'length'}")
@@ -50,33 +53,35 @@ def sync_example():
 async def async_example():
     """Asynchronous usage example."""
     print("\n=== Asynchronous vLLM-omni Example ===")
-    
+
     # Create a simple AR stage configuration
     stage_config = create_ar_stage_config(
         stage_id=0,
         model_path="Qwen/Qwen3-0.6B",
         input_modalities=["text"],
-        output_modalities=["text"]
+        output_modalities=["text"],
     )
-    
+
     # Initialize AsyncOmniLLM
     omni_llm = AsyncOmniLLM([stage_config])
-    
+
     # Prepare stage arguments
-    stage_args = [{
-        "prompt": "What is artificial intelligence?",
-        "max_tokens": 100,
-        "temperature": 0.8
-    }]
-    
+    stage_args = [
+        {
+            "prompt": "What is artificial intelligence?",
+            "max_tokens": 100,
+            "temperature": 0.8,
+        }
+    ]
+
     # Generate text asynchronously
     print(f"Input: {stage_args[0]['prompt']}")
     outputs = await omni_llm.generate_async(stage_args)
-    
+
     # Display results
     for i, output in enumerate(outputs):
         print(f"Output {i}:")
-        if hasattr(output, 'outputs') and output.outputs:
+        if hasattr(output, "outputs") and output.outputs:
             for completion in output.outputs:
                 print(f"  Text: {completion.text}")
                 print(f"  Finished: {completion.finish_reason != 'length'}")
@@ -86,36 +91,32 @@ async def async_example():
 def multi_prompt_example():
     """Example with multiple prompts."""
     print("\n=== Multi-Prompt Example ===")
-    
+
     # Create stage configuration
     stage_config = create_ar_stage_config(
         stage_id=0,
         model_path="Qwen/Qwen3-0.6B",
         input_modalities=["text"],
-        output_modalities=["text"]
+        output_modalities=["text"],
     )
-    
+
     # Initialize OmniLLM
     omni_llm = OmniLLM([stage_config])
-    
+
     # Multiple prompts
     prompts = [
         "Tell me a joke",
         "What's the weather like?",
-        "Explain quantum computing"
+        "Explain quantum computing",
     ]
-    
+
     for prompt in prompts:
         print(f"\nInput: {prompt}")
-        stage_args = [{
-            "prompt": prompt,
-            "max_tokens": 30,
-            "temperature": 0.9
-        }]
-        
+        stage_args = [{"prompt": prompt, "max_tokens": 30, "temperature": 0.9}]
+
         outputs = omni_llm.generate(stage_args)
-        
-        if outputs and hasattr(outputs[0], 'outputs') and outputs[0].outputs:
+
+        if outputs and hasattr(outputs[0], "outputs") and outputs[0].outputs:
             completion = outputs[0].outputs[0]
             print(f"Output: {completion.text}")
 
@@ -123,15 +124,15 @@ def multi_prompt_example():
 if __name__ == "__main__":
     print("vLLM-omni Simple Usage Examples")
     print("=" * 40)
-    
+
     # Run synchronous example
     sync_example()
-    
+
     # Run asynchronous example
     asyncio.run(async_example())
-    
+
     # Run multi-prompt example
     multi_prompt_example()
-    
+
     print("\n" + "=" * 40)
     print("Examples completed!")