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

[1/N][Attention] Restructure attention: move files (#31916)

Browse Source 
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
This commit is contained in:
Matthew Bonanni
2026-01-09 16:10:24 -05:00
committed by GitHub
parent 1f8b7c536b
commit 2612ba9285
195 changed files with 426 additions and 396 deletions
Download Patch File Download Diff File Expand all files Collapse all files

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

@@ -18,7 +18,6 @@ from transformers.image_utils import ImageInput
from transformers.tokenization_utils_base import TextInput
from vllm.attention.layer import Attention
from vllm.attention.layers.mm_encoder_attention import MMEncoderAttention
from vllm.compilation.decorators import support_torch_compile
from vllm.config import CacheConfig, VllmConfig
from vllm.config.multimodal import BaseDummyOptions
@@ -30,6 +29,7 @@ from vllm.distributed import (
tensor_model_parallel_all_gather,
)
from vllm.model_executor.layers.activation import MulAndSilu, QuickGELU, SiluAndMul
from vllm.model_executor.layers.attention.mm_encoder_attention import MMEncoderAttention
from vllm.model_executor.layers.layernorm import RMSNorm
from vllm.model_executor.layers.linear import (
ColumnParallelLinear,