chenchenghao/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 13 Packages Projects Releases Wiki Activity

[diffusion] improve: tiny speedup qwen-image-edit-2511 by avoiding unnecessary calculation (#15896)

Browse Source
This commit is contained in:
Mick
2025-12-30 10:10:32 +08:00
committed by GitHub
parent 3de23274ee
commit 26e17f9076
6 changed files with 53 additions and 15 deletions
Download Patch File Download Diff File Expand all files Collapse all files
python/sglang/multimodal_gen/registry.py
+2 -1
View File
@@ -28,6 +28,7 @@ from sglang.multimodal_gen.configs.pipeline_configs.base import PipelineConfig
from sglang.multimodal_gen.configs.pipeline_configs.flux import Flux2PipelineConfig
from sglang.multimodal_gen.configs.pipeline_configs.qwen_image import (
QwenImageEditPipelineConfig,
QwenImageEditPlus_2511_PipelineConfig,
QwenImageEditPlusPipelineConfig,
QwenImageLayeredPipelineConfig,
QwenImagePipelineConfig,
@@ -429,7 +430,7 @@ def _register_configs():
register_configs(
sampling_param_cls=QwenImageEditPlusSamplingParams,
pipeline_config_cls=QwenImageEditPlusPipelineConfig,
pipeline_config_cls=QwenImageEditPlus_2511_PipelineConfig,
hf_model_paths=["Qwen/Qwen-Image-Edit-2511"],
)