apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-10-05 16:48:03 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

[vl]remove duplicated load logic (#2744)
Some checks failed
Deploy GitHub Pages / deploy (push) Has been cancelled
Details

Browse Source
This commit is contained in:
bukejiyu
2025-07-13 07:36:26 +08:00
committed by GitHub
parent 16940822a7
commit bad53c6b6e
11 changed files with 510 additions and 632 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
fastdeploy/model_executor/model_loader.py
View File

@@ -28,6 +28,8 @@ from fastdeploy.model_executor.models.ernie4_5_moe import \
Ernie4_5_PretrainedModel
from fastdeploy.model_executor.models.ernie4_5_mtp import \
Ernie4_5_MTPPretrainedModel
from fastdeploy.model_executor.models.ernie4_5_vl.ernie4_5_vl_moe import \
Ernie4_5_VLPretrainedModel
from fastdeploy.model_executor.models.model_base import ModelRegistry
from fastdeploy.model_executor.models.qwen2 import Qwen2PretrainedModel
from fastdeploy.model_executor.models.qwen3 import Qwen3PretrainedModel
@@ -42,6 +44,7 @@ MODEL_CLASSES = {
"Qwen3MoeForCausalLM": Qwen3MoePretrainedModel,
"Ernie4_5_ForCausalLM": Ernie4_5_PretrainedModel,
"DeepseekV3ForCausalLM": DeepSeekV3PretrainedModel,
"Ernie4_5_VLMoeForConditionalGeneration": Ernie4_5_VLPretrainedModel,
}
@@ -94,7 +97,7 @@ class DefaultModelLoader(BaseModelLoader):
if fd_config.load_config.dynamic_load_weight:
# register rl model
import fastdeploy.rl
import fastdeploy.rl # noqa
architectures = architectures + "RL"
with context: