lint

Signed-off-by: Ekagra Ranjan <3116519+ekagra-ranjan@users.noreply.github.com>

Author: ekagra-ranjan

examples/online_serving/stable_audio/README.md

@@ -188,11 +188,11 @@ python stable_audio_client.py \
 ## Tips
 
 1. **Audio Length**: Keep under 47 seconds for `stable-audio-open-1.0`
-2. **Quality vs Speed**: 
+2. **Quality vs Speed**:
    - 50 steps: Fast, decent quality
    - 100 steps: Good balance (default)
    - 150+ steps: High quality, slower
-3. **Guidance Scale**: 
+3. **Guidance Scale**:
    - Lower (3-5): More creative/varied
    - Default (7): Good balance
    - Higher (10+): More literal to prompt

examples/online_serving/stable_audio/stable_audio_client.py

@@ -29,9 +29,7 @@
 
 
 def parse_args():
-    parser = argparse.ArgumentParser(
-        description="Generate audio with Stable Audio via OpenAI-compatible API"
-    )
+    parser = argparse.ArgumentParser(description="Generate audio with Stable Audio via OpenAI-compatible API")
     parser.add_argument(
         "--api_url",
         default="http://localhost:8000/v1/audio/speech",
@@ -93,15 +91,15 @@ def parse_args():
 
 def generate_audio(args):
     """Generate audio using the API."""
-    
+
     # Build request payload
     payload = {
         "input": args.text,
         "audio_length": args.audio_length,
         "audio_start": args.audio_start,
         "response_format": args.response_format,
     }
-    
+
     # Add optional parameters
     if args.negative_prompt:
         payload["negative_prompt"] = args.negative_prompt
@@ -111,7 +109,7 @@ def generate_audio(args):
         payload["num_inference_steps"] = args.num_inference_steps
     if args.seed is not None:
         payload["seed"] = args.seed
-    
+
     print(f"\n{'=' * 60}")
     print("Stable Audio - Text-to-Audio Generation")
     print(f"{'=' * 60}")
@@ -125,7 +123,7 @@ def generate_audio(args):
         print(f"Seed: {args.seed}")
     print(f"Output: {args.output}")
     print(f"{'=' * 60}\n")
-    
+
     try:
         # Make the API request
         print("Generating audio...")
@@ -135,21 +133,21 @@ def generate_audio(args):
             headers={"Content-Type": "application/json"},
             timeout=300,  # 5 minute timeout for long generations
         )
-        
+
         # Check for errors
         if response.status_code != 200:
             print(f"Error: API returned status code {response.status_code}")
             print(f"Response: {response.text}")
             return False
-        
+
         # Save the audio
         with open(args.output, "wb") as f:
             f.write(response.content)
-        
+
         print(f"✓ Audio saved to {args.output}")
         print(f"  File size: {len(response.content) / 1024:.1f} KB")
         return True
-        
+
     except requests.exceptions.Timeout:
         print("Error: Request timed out. Try reducing inference steps or audio length.")
         return False

vllm_omni/entrypoints/openai/api_server.py

@@ -139,7 +139,8 @@ class _DiffusionServingModels:
     """
 
     class _NullModelConfig:
-        def __getattr__(self, name): return None
+        def __getattr__(self, name):
+            return None
 
     class _Unsupported:
         def __init__(self, name: str):
@@ -151,7 +152,6 @@ def __call__(self, *args, **kwargs):
         def __getattr__(self, attr):
             raise NotImplementedError(f"{self.name}.{attr} is not supported in diffusion mode")
 
-
     def __init__(self, base_model_paths: list[BaseModelPath]) -> None:
         self._base_model_paths = base_model_paths
         self.model_config = self._NullModelConfig()
@@ -429,8 +429,8 @@ async def omni_init_app_state(
         )
 
         state.openai_serving_speech = OmniOpenAIServingSpeech.for_diffusion(
-            engine_client, 
-            state.openai_serving_models, 
+            engine_client,
+            state.openai_serving_models,
             request_logger=request_logger,
             model_name=model_name,
         )
@@ -710,10 +710,7 @@ async def omni_init_app_state(
     )
 
     state.openai_serving_speech = OmniOpenAIServingSpeech(
-        engine_client, 
-        state.openai_serving_models, 
-        request_logger=request_logger,
-        model_name=model_name
+        engine_client, state.openai_serving_models, request_logger=request_logger, model_name=model_name
     )
 
     state.enable_server_load_tracking = args.enable_server_load_tracking

vllm_omni/entrypoints/openai/audio_utils_mixin.py

@@ -44,7 +44,7 @@ def create_audio(self, audio_obj: CreateAudio) -> AudioResponse:
                 f"Unsupported audio tensor dimension: {audio_tensor.ndim}. "
                 "Only mono (1D) and stereo (2D) are supported."
             )
-        
+
         if audio_tensor.ndim == 2 and audio_tensor.shape[0] == 2:
             # Convert from [channels, samples] to [samples, channels]
             audio_tensor = audio_tensor.T

vllm_omni/entrypoints/openai/serving_speech.py

@@ -1,9 +1,9 @@
 import asyncio
 from typing import Any
 
+import torch
 from fastapi import Request
 from fastapi.responses import Response
-import torch
 from vllm.entrypoints.openai.engine.serving import OpenAIServing
 from vllm.logger import init_logger
 from vllm.utils import random_uuid
@@ -247,7 +247,7 @@ async def create_speech(
                 # Handle Stable Audio models
                 # Stable Audio uses diffusion, needs different parameters
                 default_sr = 44100  # Default sample rate for Stable Audio
-                
+
                 # Build prompt for Stable Audio
                 prompt = {
                     "prompt": request.input,
@@ -257,19 +257,20 @@ async def create_speech(
 
                 # Build sampling params for diffusion
                 sampling_params_list[0].num_outputs_per_prompt = 1
-                
+
                 # Create generator if seed provided
                 if request.seed is not None:
                     from vllm_omni.platforms import current_omni_platform
+
                     generator = torch.Generator(device=current_omni_platform.device_type).manual_seed(request.seed)
                     sampling_params_list[0].generator = generator
-                
+
                 if request.guidance_scale is not None:
                     sampling_params_list[0].guidance_scale = request.guidance_scale
-                
+
                 if request.num_inference_steps is not None:
                     sampling_params_list[0].num_inference_steps = request.num_inference_steps
-                
+
                 # Set up audio duration parameters
                 if request.audio_length is not None:
                     audio_length = request.audio_length