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 16, 03:15 UTC
Remove the duplicate imports of MultiModalKwargs and PlaceholderRange… (#11824)
WangErXiao committed
Jan 8, 2025 at 12:09 UTC
dc71af0a71f347badcd917810440fad136e73ba6
1 file changed
-2
vllm/v1/core/scheduler.py
-2
@@ -5,8 +5,6 @@ from typing import (TYPE_CHECKING, Deque, Dict, Iterable, List, Optional, Set,
5
6
from vllm.config import CacheConfig, LoRAConfig, SchedulerConfig
7
from vllm.logger import init_logger
8
-from vllm.multimodal import MultiModalKwargs
9
-from vllm.multimodal.base import PlaceholderRange
8
from vllm.sampling_params import SamplingParams
9
from vllm.v1.core.encoder_cache_manager import EncoderCacheManager
10
from vllm.v1.core.kv_cache_manager import KVCacheManager