[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

+35 -12
View File
@@ -81,6 +81,7 @@ from vllm.tool_parsers import ToolParserManager
from vllm.utils import random_uuid
from vllm.utils.system_utils import decorate_logs
from vllm_omni.diffusion.data import OmniRequestError
from vllm_omni.entrypoints.async_omni import AsyncOmni
from vllm_omni.entrypoints.openai.errors import InvalidInputReferenceError
from vllm_omni.entrypoints.openai.image_api_utils import (
@@ -1432,12 +1433,24 @@ async def edit_images(
input_images_list.extend(urls)
if not input_images_list:
raise HTTPException(status_code=422, detail="Field 'image' or 'url' is required")
pil_images = await _load_input_images(input_images_list)
if len(pil_images) > 1 and not _supports_multimodal_image_inputs(raw_request, engine_client):
# Reject oversized multi-image edit requests before fetching or decoding
# any inputs. This keeps over-limit URL requests from burning network,
# CPU, and memory on work that will be rejected anyway.
max_input_images = _get_max_edit_input_images(raw_request, engine_client)
if max_input_images is not None and len(input_images_list) > max_input_images:
detail = (
"Received multiple input images. Only a single image is supported by this model."
if max_input_images == 1
else (
f"Received {len(input_images_list)} input images. "
f"At most {max_input_images} images are supported by this model."
)
)
raise HTTPException(
status_code=HTTPStatus.BAD_REQUEST.value,
detail="Received multiple input images. Only a single image is supported by this model.",
detail=detail,
)
pil_images = await _load_input_images(input_images_list)
prompt["multi_modal_data"] = {}
prompt["multi_modal_data"]["image"] = pil_images
@@ -1601,18 +1614,25 @@ def _get_engine_and_model(raw_request: Request):
return engine_client, model_name, normalized_stage_configs
def _supports_multimodal_image_inputs(raw_request: Request, engine_client: Any) -> bool:
def _get_diffusion_od_config(raw_request: Request, engine_client: Any) -> Any:
diffusion_engine = getattr(raw_request.app.state, "diffusion_engine", None) or engine_client
get_diffusion_od_config = getattr(diffusion_engine, "get_diffusion_od_config", None)
od_config = (
return (
get_diffusion_od_config() if callable(get_diffusion_od_config) else getattr(diffusion_engine, "od_config", None)
)
def _get_max_edit_input_images(raw_request: Request, engine_client: Any) -> int | None:
od_config = _get_diffusion_od_config(raw_request, engine_client)
if od_config is None:
# Preserve the existing compatibility behavior when the diffusion
# config is not exposed on the serving surface.
return True
return bool(getattr(od_config, "supports_multimodal_inputs", False))
return None
if not bool(getattr(od_config, "supports_multimodal_inputs", False)):
return 1
return getattr(od_config, "max_multimodal_image_inputs", None)
def _get_lora_from_json_str(lora_body):
@@ -1682,11 +1702,14 @@ async def _generate_with_async_omni(
pass
sampling_params_list.append(default_stage_params)
async for output in engine_client.generate(
sampling_params_list=sampling_params_list,
**kwargs,
):
result = output
try:
async for output in engine_client.generate(
sampling_params_list=sampling_params_list,
**kwargs,
):
result = output
except OmniRequestError as e:
raise HTTPException(status_code=e.status_code, detail=str(e)) from e
if result is None:
raise HTTPException(