Merge branch 'feat/vll-m' of https://github.com/aniketmaurya/fastserv…

…e-ai into feat/vll-m

src/fastserve/models/__init__.py

@@ -5,4 +5,4 @@
 from fastserve.models.llama_cpp import ServeLlamaCpp as ServeLlamaCpp
 from fastserve.models.sdxl_turbo import ServeSDXLTurbo as ServeSDXLTurbo
 from fastserve.models.ssd import ServeSSD1B as ServeSSD1B
-from fastserve.models.vllm import ServeVLLM as ServeVLLM
+from fastserve.models.vllm import ServeVLLM as ServeVLLM

src/fastserve/models/vllm.py

@@ -1,15 +1,13 @@
 import logging
-import os
 from typing import Any, List, Optional
 
-from pydantic import BaseModel, Field
+from pydantic import BaseModel
 
 from fastserve.core import FastServe
 
 logger = logging.getLogger(__name__)
 
 
-
 class PromptRequest(BaseModel):
     prompt: str = "Write a python function to resize image to 224x224"
     temperature: float = 0.8
@@ -50,8 +48,9 @@ def __call__(self, request: PromptRequest) -> Any:
         from vllm import SamplingParams
 
         sampling_params = SamplingParams(
-            temperature=request.temperature, top_p=request.top_p,
-            max_tokens=request.max_tokens
+            temperature=request.temperature,
+            top_p=request.top_p,
+            max_tokens=request.max_tokens,
         )
         result = self.llm.generate(request.prompt, sampling_params=sampling_params)
         logger.info(result)