Merge branch 'vllm-project-main' into image_bench-on-refactor

benchmarks/benchmark_throughput.py

@@ -5,7 +5,6 @@
 import random
 import time
 from typing import List, Optional
-from typing import List, Optional
 
 import torch
 import uvloop
@@ -23,23 +22,6 @@
 from vllm.utils import FlexibleArgumentParser, merge_async_iterators
 
 
-@dataclasses.dataclass
-class SampleRequest:
-    """A class representing a single inference request for benchmarking.
-
-    Attributes:
-        prompt: The input text prompt for the model.
-        multi_modal_data: Optional dictionary containing multi-modal data (e.g.
-            images).
-        prompt_len: The length of the prompt in tokens.
-        expected_output_len: The expected length of the output in tokens.
-    """
-    prompt: str
-    prompt_len: int
-    expected_output_len: int
-    multi_modal_data: Optional[MultiModalDataDict] = None
-
-
 @dataclasses.dataclass
 class SampleRequest:
     """A class representing a single inference request for benchmarking.