[Rebase] Rebase to vllm v0.16.0 (#1357)
ComfyUI Integration -- Publish to Comfy registry / Publish Custom Node to registry (push) Failing after 44s

Signed-off-by: Taichang Zhou <tzhouam@connect.ust.hk>
Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
Signed-off-by: princepride <wangzhipeng628@gmail.com>
Co-authored-by: 汪志鹏 <wangzhipeng628@gmail.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
Co-authored-by: Isotr0py <Isotr0py@outlook.com>
Co-authored-by: ZJY0516 <zhu.jiangyun@foxmail.com>
Co-authored-by: youkaichao <youkaichao@gmail.com>
This commit is contained in:
authored and GitHub committed 2026-02-13 18:05:07 +08:00
1 parent 630e84ef93
commit 75770c9309
40 files changed
+1210 -1264

No files matched your search

+12 -4
View File
@@ -31,9 +31,15 @@ from vllm.entrypoints.chat_utils import load_chat_template
from vllm.entrypoints.launcher import serve_http
from vllm.entrypoints.logger import RequestLogger
from vllm.entrypoints.mcp.tool_server import DemoToolServer, MCPToolServer, ToolServer
from vllm.entrypoints.openai.api_server import base, load_log_config
from vllm.entrypoints.openai.api_server import build_app as build_openai_app
from vllm.entrypoints.openai.api_server import setup_server as setup_openai_server
# vLLM moved `base` from openai.basic.api_router to serve.instrumentator.basic.
# Keep a fallback for older/newer upstream layouts during rebase windows.
try:
from vllm.entrypoints.serve.instrumentator.basic import base
except ModuleNotFoundError:
from vllm.entrypoints.openai.basic.api_router import base
from vllm.entrypoints.openai.chat_completion.protocol import (
ChatCompletionRequest,
ChatCompletionResponse,
@@ -53,7 +59,8 @@ from vllm.entrypoints.openai.models.protocol import BaseModelPath
from vllm.entrypoints.openai.models.serving import OpenAIServingModels
from vllm.entrypoints.openai.orca_metrics import metrics_header
from vllm.entrypoints.openai.responses.serving import OpenAIServingResponses
from vllm.entrypoints.openai.translations.serving import (
from vllm.entrypoints.openai.server_utils import get_uvicorn_log_config
from vllm.entrypoints.openai.speech_to_text.serving import (
OpenAIServingTranscription,
OpenAIServingTranslation,
)
@@ -195,7 +202,7 @@ async def omni_run_server_worker(listen_address, sock, args, client_config=None,
ReasoningParserManager.import_reasoning_parser(args.reasoning_parser_plugin)
# Load logging config for uvicorn if specified
log_config = load_log_config(getattr(args, "log_config_file", None))
log_config = get_uvicorn_log_config(args)
if log_config is not None:
uvicorn_kwargs["log_config"] = log_config
@@ -211,7 +218,8 @@ async def omni_run_server_worker(listen_address, sock, args, client_config=None,
if not supported_tasks:
supported_tasks = ("generate",)
app = build_openai_app(args)
# OMNI: Pass supported_tasks to build_app (required by upstream vLLM)
app = build_openai_app(args, supported_tasks)
# OMNI: Remove upstream routes that we override with omni-specific handlers
_remove_route_from_app(app, "/v1/chat/completions", {"POST"})
_remove_route_from_app(app, "/v1/models", {"GET"}) # Remove upstream /v1/models to use omni's handler