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 9, 07:30 UTC
fix QERL attention import path (#33432)
Signed-off-by: vasiliy <vasiliy@fb.com> Signed-off-by: Michael Goin <mgoin64@gmail.com> Co-authored-by: Michael Goin <mgoin64@gmail.com>
Vasiliy Kuznetsov committed
Jan 30, 2026 at 12:29 UTC
3f96fcf64631a100904bb189859f9aa80e8a75d5
1 file changed
+1
-1
vllm/model_executor/model_loader/reload/layerwise.py
+1
-1
@@ -7,9 +7,9 @@ from weakref import WeakKeyDictionary
7
8
import torch
9
10
-from vllm.attention.layer import Attention, MLAAttention
10
from vllm.config import ModelConfig
11
from vllm.logger import init_logger
12
+from vllm.model_executor.layers.attention import Attention, MLAAttention
13
from vllm.model_executor.layers.quantization.base_config import QuantizeMethodBase
14
from vllm.model_executor.model_loader.weight_utils import default_weight_loader
15