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 17, 04:15 UTC
fix relative import path of protocol.py (#3134)
Co-authored-by: huohuarong <huohuarong@zuoshouyisheng.com>
Huarong committed
Mar 2, 2024 at 03:42 UTC
90fbf12540da089fcc7dc825ce2ceb7ea3a3df33
1 file changed
+1
-1
vllm/entrypoints/openai/serving_completion.py
+1
-1
@@ -5,7 +5,7 @@ from typing import AsyncGenerator, AsyncIterator, Callable, List, Optional, Dict
5
from vllm.logger import init_logger
6
from vllm.utils import random_uuid
7
from vllm.engine.async_llm_engine import AsyncLLMEngine
8
-from .protocol import (
8
+from vllm.entrypoints.openai.protocol import (
9
CompletionRequest,
10
CompletionResponse,
11
CompletionResponseChoice,