chenchenghao/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 11 Packages Projects Releases Wiki Activity

diffusion: reduce effort of supporting new model (#12982)

Browse Source
This commit is contained in:
Mick
2025-11-10 21:20:33 +08:00
committed by GitHub
parent afee2843d5
commit 5639145fac
66 changed files with 667 additions and 2385 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
python/sglang/multimodal_gen/runtime/managers/gpu_worker.py
View File

@@ -16,8 +16,8 @@ from sglang.multimodal_gen.runtime.distributed.parallel_state import (
get_cfg_group,
get_tp_group,
)
from sglang.multimodal_gen.runtime.pipelines import build_pipeline
from sglang.multimodal_gen.runtime.pipelines.pipeline_batch_info import OutputBatch, Req
from sglang.multimodal_gen.runtime.pipelines import Req, build_pipeline
from sglang.multimodal_gen.runtime.pipelines.schedule_batch import OutputBatch
from sglang.multimodal_gen.runtime.server_args import PortArgs, ServerArgs
from sglang.multimodal_gen.runtime.utils.common import set_cuda_arch
from sglang.multimodal_gen.runtime.utils.logging_utils import (