[cherry-pick][release/v0.18.0.post1] cherry-pick #2847 #2780 #2840 #2876 #2877 (#2878)

Signed-off-by: david6666666 <530634352@qq.com>
Signed-off-by: David Chen <530634352@qq.com>
Signed-off-by: WeiQing Chen <40507679+david6666666@users.noreply.github.com>
This commit is contained in:
WeiQing Chen authored and GitHub committed 2026-04-20 11:14:12 +08:00
1 parent 783086bcbf
commit 2116e88638
25 files changed
+1069 -86

No files matched your search

+9 -2
View File
@@ -17,6 +17,7 @@ from vllm.model_executor.layers.quantization.base_config import (
QuantizationConfig,
)
from vllm_omni.diffusion.model_metadata import get_diffusion_model_metadata
from vllm_omni.diffusion.utils.network_utils import is_port_available
from vllm_omni.quantization import build_quant_config
@@ -468,8 +469,10 @@ class OmniDiffusionConfig:
# Scheduler flow_shift for Wan2.2 (12.0 for 480p, 5.0 for 720p)
flow_shift: float | None = None
# support multi images input
# Support multi-image inputs and expose any model-specific request limit
# through a generic config field so serving code stays model-agnostic.
supports_multimodal_inputs: bool = False
max_multimodal_image_inputs: int | None = None
log_level: str = "info"
@@ -615,7 +618,11 @@ class OmniDiffusionConfig:
raise ValueError("max_cpu_loras must be >= 1 for diffusion LoRA")
def update_multimodal_support(self) -> None:
self.supports_multimodal_inputs = self.model_class_name in {"QwenImageEditPlusPipeline"}
# Resolve serving-visible multimodal behavior from shared metadata
# instead of importing concrete pipeline modules into the config layer.
metadata = get_diffusion_model_metadata(self.model_class_name)
self.supports_multimodal_inputs = metadata.supports_multimodal_inputs
self.max_multimodal_image_inputs = metadata.max_multimodal_image_inputs
def enrich_config(self) -> None:
"""Load model metadata from HuggingFace and populate config fields.