Production runs one static model behind the OpenAI-compatible API. Every adapter path and non-OpenAI HTTP surface is unreachable there. - Delete the LoRA stack: vllm/lora, LoRARequest on the engine wire, the scheduler, worker, cudagraph and MoE plumbing, LoRA metrics, the lora CLI group, and the LoRA tests. - Drop the plugin loader in vllm/plugins. Platform resolution is now CUDA-only and the general/stat-logger plugin hooks are gone. - Delete the speech-to-text and realtime entrypoints, the scale-out render routes, and vllm/config/speech_to_text.py. GenerationTask is generate-only. - Cut DecodeBenchConnector and the disagg-prefill doc and image. The Multi, Offloading and Example connectors stay; production uses the CPU KV offload tier. - Delete the ROCm-only fused KDA chunk kernel (2346 lines) with its CMake arch gate, declarations and op registrations. The CUDA build never defined the guard and no Python caller existed. - Delete the orphan Mistral and Pixtral chat fixtures and examples/. - Fix _check_model: removing the LoRA early return made every request fail with "The model ... does not exist. Valid aliases: ...". Verified on an RTX 3090: import sweep reports 1242 modules with 7 known optional-dependency failures; a live server answers chat, completions, responses, tokenize and detokenize with zero log errors and 404 for the removed surfaces; collection yields 8558 tests with the 3 pre-existing errors; ruff adds no new finding; the incremental _C build succeeds. Co-authored-by: Hinata <hinata@idihore.id> Signed-off-by: MOVZX <movzx@yahoo.com>
46 lines
1.5 KiB
Python
46 lines
1.5 KiB
Python
# SPDX-License-Identifier: Apache-2.0
|
|
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
|
|
import warnings
|
|
from argparse import Namespace
|
|
|
|
from fastapi import FastAPI
|
|
|
|
from vllm.config import ModelConfig
|
|
from vllm.entrypoints.serve.exception_handling.register import init_exception_handler
|
|
from vllm.entrypoints.serve.middleware.register import init_entrypoints_middleware
|
|
from vllm.tasks import FALLBACK_SUPPORTED_TASKS, SupportedTask
|
|
|
|
from .api_server.routers import register_api_routers
|
|
from .utils.server_utils import lifespan
|
|
|
|
|
|
def build_app(
|
|
args: Namespace,
|
|
supported_tasks: tuple["SupportedTask", ...] | None = None,
|
|
model_config: ModelConfig | None = None,
|
|
) -> FastAPI:
|
|
if supported_tasks is None:
|
|
warnings.warn(
|
|
"The 'supported_tasks' parameter was not provided to "
|
|
"build_app and will be required in a future version. "
|
|
"Defaulting to ('generate',).",
|
|
DeprecationWarning,
|
|
stacklevel=2,
|
|
)
|
|
supported_tasks = FALLBACK_SUPPORTED_TASKS
|
|
|
|
if args.disable_fastapi_docs:
|
|
app = FastAPI(
|
|
openapi_url=None, docs_url=None, redoc_url=None, lifespan=lifespan
|
|
)
|
|
else:
|
|
app = FastAPI(docs_url=None, redoc_url=None, lifespan=lifespan)
|
|
app.state.args = args
|
|
app.root_path = args.root_path
|
|
|
|
register_api_routers(args, app, supported_tasks, model_config)
|
|
|
|
init_exception_handler(app)
|
|
init_entrypoints_middleware(args, app, supported_tasks)
|
|
return app
|