biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

fix QERL attention import path (#33432)

Browse Source 
Signed-off-by: vasiliy <vasiliy@fb.com>
Signed-off-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
This commit is contained in:
Vasiliy Kuznetsov
2026-01-30 12:29:09 -05:00
committed by GitHub
parent 6c1f9e4c18
commit 3f96fcf646
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
vllm/model_executor/model_loader/reload/layerwise.py
View File

@@ -7,9 +7,9 @@ from weakref import WeakKeyDictionary
import torch import torch
from vllm.attention.layer import Attention, MLAAttention
from vllm.config import ModelConfig from vllm.config import ModelConfig
from vllm.logger import init_logger from vllm.logger import init_logger
from vllm.model_executor.layers.attention import Attention, MLAAttention
from vllm.model_executor.layers.quantization.base_config import QuantizeMethodBase from vllm.model_executor.layers.quantization.base_config import QuantizeMethodBase
from vllm.model_executor.model_loader.weight_utils import default_weight_loader from vllm.model_executor.model_loader.weight_utils import default_weight_loader