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

[5/N][Attention] Finish eliminating vllm/attention folder (#32064)

Browse Source 
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
This commit is contained in:
Matthew Bonanni
2026-01-27 10:02:51 -05:00
committed by GitHub
parent 1f3a2c2944
commit a608b4c6c2
151 changed files with 585 additions and 527 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
vllm/model_executor/models/deepencoder.py
View File

@@ -18,7 +18,7 @@ import torch.nn as nn
import torch.nn.functional as F
from transformers import CLIPVisionConfig
from vllm.model_executor.layers.attention.mm_encoder_attention import MMEncoderAttention
from vllm.model_executor.layers.attention import MMEncoderAttention
from vllm.model_executor.layers.conv import Conv2dLayer
from vllm.model_executor.layers.quantization import QuantizationConfig
from vllm.model_executor.model_loader.weight_utils import default_weight_loader