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

Refactor Transformers backend to use mixins (#26906)

Browse Source 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
This commit is contained in:
Harry Mellor
2025-10-16 22:50:39 +01:00
committed by GitHub
parent b2f78cbad4
commit fb5e10d3fb
17 changed files with 1510 additions and 1248 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
vllm/model_executor/models/deepseek_vl2.py
View File

@@ -19,7 +19,7 @@ from vllm.config.multimodal import BaseDummyOptions
from vllm.distributed import get_tensor_model_parallel_world_size
from vllm.model_executor.layers.quantization import QuantizationConfig
from vllm.model_executor.model_loader.utils import set_default_torch_dtype
from vllm.model_executor.models.transformers import replace_linear_class
from vllm.model_executor.models.transformers.utils import replace_linear_class
from vllm.multimodal import MULTIMODAL_REGISTRY
from vllm.multimodal.inputs import (
MultiModalDataDict,