A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 12, 11:00 UTC
[Misc] Remove unused code from `protocol.py` (#29616)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Cyrus Leung committed
Nov 28, 2025 at 02:39 UTC
ea228b4491342f6b7a283e1a414e1a75171a0241
1 file changed
-9
vllm/engine/protocol.py
-9
@@ -1,14 +1,12 @@
1
# SPDX-License-Identifier: Apache-2.0
2
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
3
4
-import enum
4
from abc import ABC, abstractmethod
5
from collections.abc import AsyncGenerator, Iterable, Mapping
6
from typing import Any
7
8
from vllm.config import ModelConfig, VllmConfig
9
from vllm.inputs.data import PromptType
11
-from vllm.logger import init_logger
10
from vllm.lora.request import LoRARequest
11
from vllm.outputs import PoolingRequestOutput, RequestOutput
12
from vllm.plugins.io_processors import IOProcessor
@@ -19,13 +17,6 @@ from vllm.transformers_utils.tokenizer import AnyTokenizer
17
from vllm.v1.engine import EngineCoreRequest
18
from vllm.v1.engine.processor import Processor
19
22
-logger = init_logger(__name__)
23
-
24
-
25
-class Device(enum.Enum):
26
- GPU = enum.auto()
27
- CPU = enum.auto()
28
-
20
21
class EngineClient(ABC):
22
"""Protocol class for Clients to Engine"""