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

3
vllm/model_executor/models/molmo.py
View File

@@ -17,7 +17,6 @@ from transformers import BatchFeature, PretrainedConfig, ProcessorMixin, TensorT
from transformers.image_utils import ImageInput
from transformers.tokenization_utils_base import TextInput
from vllm.attention.layer import Attention
from vllm.compilation.decorators import support_torch_compile
from vllm.config import CacheConfig, VllmConfig
from vllm.config.multimodal import BaseDummyOptions
@@ -29,7 +28,7 @@ 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.attention import Attention, MMEncoderAttention
from vllm.model_executor.layers.layernorm import RMSNorm
from vllm.model_executor.layers.linear import (
ColumnParallelLinear,