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>
117 lines
4.2 KiB
Python
117 lines
4.2 KiB
Python
# SPDX-License-Identifier: Apache-2.0
|
|
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
|
|
import warnings
|
|
from argparse import Namespace
|
|
from typing import cast
|
|
|
|
from starlette.datastructures import State
|
|
|
|
from vllm.engine.protocol import EngineClient
|
|
from vllm.entrypoints.mcp.tool_server import init_tool_server
|
|
from vllm.entrypoints.openai.models.protocol import BaseModelPath
|
|
from vllm.entrypoints.openai.models.serving import OpenAIServingModels
|
|
from vllm.entrypoints.serve.tokenize.serving import ServingTokenization
|
|
from vllm.entrypoints.serve.utils.request_logger import RequestLogger
|
|
from vllm.renderers.chat_utils import load_chat_template
|
|
from vllm.renderers.online_renderer import OnlineRenderer
|
|
from vllm.tasks import FALLBACK_SUPPORTED_TASKS, SupportedTask
|
|
|
|
|
|
async def init_app_state(
|
|
engine_client: EngineClient,
|
|
state: State,
|
|
args: Namespace,
|
|
supported_tasks: tuple["SupportedTask", ...] | None = None,
|
|
) -> None:
|
|
vllm_config = engine_client.vllm_config
|
|
|
|
if args.tool_call_parser is not None:
|
|
from vllm.parser.metrics import init_parser_metrics
|
|
|
|
init_parser_metrics(
|
|
model_name=cast(str, vllm_config.model_config.served_model_name)
|
|
)
|
|
|
|
if supported_tasks is None:
|
|
warnings.warn(
|
|
"The 'supported_tasks' parameter was not provided to "
|
|
"init_app_state and will be required in a future version. "
|
|
"Please pass 'supported_tasks' explicitly.",
|
|
DeprecationWarning,
|
|
stacklevel=2,
|
|
)
|
|
supported_tasks = FALLBACK_SUPPORTED_TASKS
|
|
|
|
if args.served_model_name is not None:
|
|
served_model_names = args.served_model_name
|
|
else:
|
|
served_model_names = [args.model]
|
|
|
|
if args.enable_log_requests:
|
|
request_logger = RequestLogger(max_log_len=args.max_log_len)
|
|
else:
|
|
request_logger = None
|
|
|
|
base_model_paths = [
|
|
BaseModelPath(name=name, model_path=args.model) for name in served_model_names
|
|
]
|
|
|
|
state.engine_client = engine_client
|
|
state.log_stats = not args.disable_log_stats
|
|
state.vllm_config = vllm_config
|
|
state.args = args
|
|
resolved_chat_template = load_chat_template(args.chat_template)
|
|
default_chat_template_kwargs = dict(args.default_chat_template_kwargs or {})
|
|
state.tool_server = (
|
|
await init_tool_server(args) if "generate" in supported_tasks else None
|
|
)
|
|
|
|
state.openai_serving_models = OpenAIServingModels(
|
|
engine_client=engine_client,
|
|
base_model_paths=base_model_paths,
|
|
)
|
|
|
|
state.online_renderer = OnlineRenderer(
|
|
model_config=engine_client.model_config,
|
|
renderer=engine_client.renderer,
|
|
request_logger=request_logger,
|
|
chat_template=resolved_chat_template,
|
|
chat_template_content_format=args.chat_template_content_format,
|
|
trust_request_chat_template=args.trust_request_chat_template,
|
|
trust_request_mm_kwargs=args.trust_request_mm_kwargs,
|
|
enable_auto_tools=args.enable_auto_tool_choice,
|
|
exclude_tools_when_tool_choice_none=args.exclude_tools_when_tool_choice_none,
|
|
tool_parser=args.tool_call_parser,
|
|
tool_strict_level=args.tool_strict_level,
|
|
reasoning_parser=args.structured_outputs_config.reasoning_parser,
|
|
default_chat_template_kwargs=default_chat_template_kwargs,
|
|
log_error_stack=args.log_error_stack,
|
|
)
|
|
state.online_renderer.warmup()
|
|
|
|
state.serving_tokenization = ServingTokenization(
|
|
state.openai_serving_models,
|
|
state.online_renderer,
|
|
request_logger=request_logger,
|
|
chat_template=resolved_chat_template,
|
|
chat_template_content_format=args.chat_template_content_format,
|
|
default_chat_template_kwargs=default_chat_template_kwargs,
|
|
trust_request_chat_template=args.trust_request_chat_template,
|
|
)
|
|
|
|
if "generate" in supported_tasks:
|
|
from vllm.entrypoints.generate.api_router import init_generate_state
|
|
|
|
await init_generate_state(
|
|
engine_client,
|
|
state,
|
|
args,
|
|
request_logger,
|
|
supported_tasks,
|
|
default_chat_template_kwargs,
|
|
)
|
|
|
|
|
|
state.enable_server_load_tracking = args.enable_server_load_tracking
|
|
state.server_load_metrics = 0
|