xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-13 13:55:01 +08:00
Code Issues Packages Projects Releases Wiki Activity

refactor(benchmarks): add type annotations to wait_for_endpoint parameters (#25218)

Browse Source 
Signed-off-by: samzong <samzong.lu@gmail.com>
This commit is contained in:
samzong 2025-09-20 00:36:52 +08:00 committed by GitHub
parent aed16879a9
commit ce75e15373
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 16 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
vllm/benchmarks/lib/endpoint_request_func.py
View File

@ -8,8 +8,9 @@ import os
import sys import sys
import time import time
import traceback import traceback
from collections.abc import Awaitable
from dataclasses import dataclass, field from dataclasses import dataclass, field
from typing import Optional, Union from typing import Optional, Protocol, Union
import aiohttp import aiohttp
from tqdm.asyncio import tqdm from tqdm.asyncio import tqdm
@ -92,6 +93,16 @@ class RequestFuncOutput:
start_time: float = 0.0 start_time: float = 0.0
class RequestFunc(Protocol):
def __call__(
self,
request_func_input: RequestFuncInput,
session: aiohttp.ClientSession,
pbar: Optional[tqdm] = None,
) -> Awaitable[RequestFuncOutput]:
...
async def async_request_openai_completions( async def async_request_openai_completions(
request_func_input: RequestFuncInput, request_func_input: RequestFuncInput,
session: aiohttp.ClientSession, session: aiohttp.ClientSession,
@ -507,7 +518,7 @@ async def async_request_openai_embeddings(
# TODO: Add more request functions for different API protocols. # TODO: Add more request functions for different API protocols.
ASYNC_REQUEST_FUNCS = { ASYNC_REQUEST_FUNCS: dict[str, RequestFunc] = {
"vllm": async_request_openai_completions, "vllm": async_request_openai_completions,
"openai": async_request_openai_completions, "openai": async_request_openai_completions,
"openai-chat": async_request_openai_chat_completions, "openai-chat": async_request_openai_chat_completions,

5
vllm/benchmarks/lib/ready_checker.py
View File

@ -8,11 +8,12 @@ import time
import aiohttp import aiohttp
from tqdm.asyncio import tqdm from tqdm.asyncio import tqdm
from .endpoint_request_func import RequestFuncInput, RequestFuncOutput from .endpoint_request_func import (RequestFunc, RequestFuncInput,
RequestFuncOutput)
async def wait_for_endpoint( async def wait_for_endpoint(
request_func, request_func: RequestFunc,
test_input: RequestFuncInput, test_input: RequestFuncInput,
session: aiohttp.ClientSession, session: aiohttp.ClientSession,
timeout_seconds: int = 600, timeout_seconds: int = 600,