[Frontend] Make TIMEOUT_KEEP_ALIVE configurable through env var (#18472)

Signed-off-by: liusiqian <liusiqian@tal.com>

tests/async_engine/api_server_async_engine.py

@@ -8,6 +8,7 @@ import uvicorn
 from fastapi.responses import JSONResponse, Response
 
 import vllm.entrypoints.api_server
+import vllm.envs as envs
 from vllm.engine.arg_utils import AsyncEngineArgs
 from vllm.engine.async_llm_engine import AsyncLLMEngine
 from vllm.utils import FlexibleArgumentParser
@@ -46,9 +47,8 @@ if __name__ == "__main__":
     engine_args = AsyncEngineArgs.from_cli_args(args)
     engine = AsyncLLMEngineWithStats.from_engine_args(engine_args)
     vllm.entrypoints.api_server.engine = engine
-    uvicorn.run(
-        app,
-        host=args.host,
-        port=args.port,
-        log_level="debug",
-        timeout_keep_alive=vllm.entrypoints.api_server.TIMEOUT_KEEP_ALIVE)
+    uvicorn.run(app,
+                host=args.host,
+                port=args.port,
+                log_level="debug",
+                timeout_keep_alive=envs.VLLM_HTTP_TIMEOUT_KEEP_ALIVE)

vllm/entrypoints/api_server.py

@@ -17,6 +17,7 @@ from typing import Any, Optional
 from fastapi import FastAPI, Request
 from fastapi.responses import JSONResponse, Response, StreamingResponse
 
+import vllm.envs as envs
 from vllm.engine.arg_utils import AsyncEngineArgs
 from vllm.engine.async_llm_engine import AsyncLLMEngine
 from vllm.entrypoints.launcher import serve_http
@@ -29,7 +30,6 @@ from vllm.version import __version__ as VLLM_VERSION
 
 logger = init_logger("vllm.entrypoints.api_server")
 
-TIMEOUT_KEEP_ALIVE = 5  # seconds.
 app = FastAPI()
 engine = None
 
@@ -134,7 +134,7 @@ async def run_server(args: Namespace,
         host=args.host,
         port=args.port,
         log_level=args.log_level,
-        timeout_keep_alive=TIMEOUT_KEEP_ALIVE,
+        timeout_keep_alive=envs.VLLM_HTTP_TIMEOUT_KEEP_ALIVE,
         ssl_keyfile=args.ssl_keyfile,
         ssl_certfile=args.ssl_certfile,
         ssl_ca_certs=args.ssl_ca_certs,

vllm/entrypoints/openai/api_server.py

@@ -103,8 +103,6 @@ from vllm.utils import (Device, FlexibleArgumentParser, get_open_zmq_ipc_path,
 from vllm.v1.metrics.prometheus import get_prometheus_registry
 from vllm.version import __version__ as VLLM_VERSION
 
-TIMEOUT_KEEP_ALIVE = 5  # seconds
-
 prometheus_multiproc_dir: tempfile.TemporaryDirectory
 
 # Cannot use __name__ (https://github.com/vllm-project/vllm/pull/4765)
@@ -1360,7 +1358,7 @@ async def run_server_worker(listen_address,
             # NOTE: When the 'disable_uvicorn_access_log' value is True,
             # no access log will be output.
             access_log=not args.disable_uvicorn_access_log,
-            timeout_keep_alive=TIMEOUT_KEEP_ALIVE,
+            timeout_keep_alive=envs.VLLM_HTTP_TIMEOUT_KEEP_ALIVE,
             ssl_keyfile=args.ssl_keyfile,
             ssl_certfile=args.ssl_certfile,
             ssl_ca_certs=args.ssl_ca_certs,

vllm/envs.py

@@ -71,6 +71,7 @@ if TYPE_CHECKING:
     VERBOSE: bool = False
     VLLM_ALLOW_LONG_MAX_MODEL_LEN: bool = False
     VLLM_RPC_TIMEOUT: int = 10000  # ms
+    VLLM_HTTP_TIMEOUT_KEEP_ALIVE: int = 5  # seconds
     VLLM_PLUGINS: Optional[list[str]] = None
     VLLM_LORA_RESOLVER_CACHE_DIR: Optional[str] = None
     VLLM_TORCH_PROFILER_DIR: Optional[str] = None
@@ -557,6 +558,10 @@ environment_variables: dict[str, Callable[[], Any]] = {
     "VLLM_RPC_TIMEOUT":
     lambda: int(os.getenv("VLLM_RPC_TIMEOUT", "10000")),
 
+    # Timeout in seconds for keeping HTTP connections alive in API server
+    "VLLM_HTTP_TIMEOUT_KEEP_ALIVE":
+    lambda: int(os.environ.get("VLLM_HTTP_TIMEOUT_KEEP_ALIVE", "5")),
+
     # a list of plugin names to load, separated by commas.
     # if this is not set, it means all plugins will be loaded
     # if this is set to an empty string, no plugins will be loaded