[Frontend] Move api_server.py out openai folder (#52131)
Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
This commit is contained in:
@@ -3,18 +3,11 @@
|
||||
|
||||
import argparse
|
||||
import inspect
|
||||
import signal
|
||||
|
||||
import uvloop
|
||||
|
||||
from vllm import envs
|
||||
from vllm.config import VllmConfig
|
||||
from vllm.engine.arg_utils import AsyncEngineArgs
|
||||
from vllm.entrypoints.cli.types import CLISubcommand
|
||||
from vllm.entrypoints.openai.api_server import (
|
||||
build_and_serve_renderer,
|
||||
setup_server,
|
||||
)
|
||||
from vllm.entrypoints.launchers.render.entry import run_launch_fastapi
|
||||
from vllm.entrypoints.openai.cli_args import (
|
||||
make_arg_parser,
|
||||
validate_parsed_serve_args,
|
||||
@@ -120,38 +113,3 @@ class LaunchSubcommand(CLISubcommand):
|
||||
|
||||
def cmd_init() -> list[CLISubcommand]:
|
||||
return [LaunchSubcommand()]
|
||||
|
||||
|
||||
async def run_launch_fastapi(args: argparse.Namespace) -> None:
|
||||
"""Run the online serving layer with FastAPI (no GPU inference)."""
|
||||
|
||||
# Interrupt initialization if SIGTERM arrives before uvicorn installs
|
||||
# its own signal handlers. Once uvicorn is running it replaces this.
|
||||
def _interrupt_init(*_) -> None:
|
||||
raise KeyboardInterrupt("terminated")
|
||||
|
||||
signal.signal(signal.SIGTERM, _interrupt_init)
|
||||
|
||||
# 1. Socket binding
|
||||
listen_address, sock = setup_server(args, reuse_port=False)
|
||||
|
||||
# 2. Build and serve the API server
|
||||
engine_args = AsyncEngineArgs.from_cli_args(args)
|
||||
model_config = engine_args.create_model_config()
|
||||
|
||||
# Render servers preprocess data only — no inference, no quantized kernels.
|
||||
# Clear quantization so VllmConfig skips quant dtype/capability validation.
|
||||
model_config.quantization = None
|
||||
|
||||
# Render servers never allocate KV cache; suppress the spurious CPU KV
|
||||
# cache space warning from CpuPlatform.check_and_update_config.
|
||||
envs.VLLM_CPU_KVCACHE_SPACE = 0
|
||||
|
||||
vllm_config = VllmConfig(model_config=model_config)
|
||||
shutdown_task = await build_and_serve_renderer(
|
||||
vllm_config, listen_address, sock, args
|
||||
)
|
||||
try:
|
||||
await shutdown_task
|
||||
finally:
|
||||
sock.close()
|
||||
|
||||
@@ -10,11 +10,9 @@ import uvloop
|
||||
import vllm
|
||||
import vllm.envs as envs
|
||||
from vllm.entrypoints.cli.types import CLISubcommand
|
||||
from vllm.entrypoints.openai.api_server import run_server, setup_server
|
||||
from vllm.entrypoints.launchers.api_server.entry import run_server, setup_server
|
||||
from vllm.entrypoints.openai.cli_args import make_arg_parser, validate_parsed_serve_args
|
||||
from vllm.entrypoints.openai.dp_supervisor import (
|
||||
run_dp_supervisor,
|
||||
)
|
||||
from vllm.entrypoints.openai.dp_supervisor import run_dp_supervisor
|
||||
from vllm.entrypoints.serve.utils.api_utils import VLLM_SUBCMD_PARSER_EPILOG
|
||||
from vllm.logger import init_logger
|
||||
from vllm.usage.usage_lib import UsageContext
|
||||
|
||||
Reference in New Issue
Block a user