Skip to content

Fix aiohttp 'Chunk too big' in bench_serving #6737

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 3 commits into from
May 30, 2025
Merged

Fix aiohttp 'Chunk too big' in bench_serving #6737

Changes from 1 commit
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
abc361a
Fix aiohttp 'Chunk too big'
guoyuhong May 28, 2025
2d88e91
Update python/sglang/bench_serving.py according to code assistent.
guoyuhong May 29, 2025
222e4dd
Python lint
guoyuhong May 29, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
18 changes: 12 additions & 6 deletions python/sglang/bench_serving.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -39,7 +39,6 @@
PreTrainedTokenizerFast,
)

AIOHTTP_TIMEOUT = aiohttp.ClientTimeout(total=6 * 60 * 60)
ASSISTANT_SUFFIX = "Assistant:"

global args
Expand All @@ -51,6 +50,13 @@ def _get_bool_env_var(name: str, default: str = "false") -> bool:
return value.lower() in ("true", "1")


def _create_bench_client_session():
# When the pressure is big, the read buffer could be full before aio thread read
# the content. We increase the read_bufsize from 64K to 10M.
aiohttp_timeout = aiohttp.ClientTimeout(total=6 * 60 * 60)
return aiohttp.ClientSession(timeout=aiohttp_timeout, read_bufsize=10 * 1024**2)


@dataclass
class RequestFuncInput:
prompt: str
Expand Down Expand Up @@ -106,7 +112,7 @@ async def async_request_trt_llm(
api_url = request_func_input.api_url
assert api_url.endswith("generate_stream")

async with aiohttp.ClientSession(timeout=AIOHTTP_TIMEOUT) as session:
async with _create_bench_client_session() as session:
payload = {
"accumulate_tokens": True,
"text_input": request_func_input.prompt,
Expand Down Expand Up @@ -179,7 +185,7 @@ async def async_request_openai_completions(

prompt = request_func_input.prompt

async with aiohttp.ClientSession(timeout=AIOHTTP_TIMEOUT) as session:
async with _create_bench_client_session() as session:
payload = {
"model": request_func_input.model,
"prompt": prompt,
Expand Down Expand Up @@ -261,7 +267,7 @@ async def async_request_truss(

prompt = request_func_input.prompt

async with aiohttp.ClientSession(timeout=AIOHTTP_TIMEOUT) as session:
async with _create_bench_client_session() as session:
payload = {
"model": request_func_input.model,
"prompt": prompt,
Expand Down Expand Up @@ -338,7 +344,7 @@ async def async_request_sglang_generate(
api_url = request_func_input.api_url
prompt = request_func_input.prompt

async with aiohttp.ClientSession(timeout=AIOHTTP_TIMEOUT) as session:
async with _create_bench_client_session() as session:
payload = {
("text" if isinstance(prompt, str) else "input_ids"): prompt,
"sampling_params": {
Expand Down Expand Up @@ -437,7 +443,7 @@ async def async_request_gserver(


async def async_request_profile(api_url: str) -> RequestFuncOutput:
async with aiohttp.ClientSession(timeout=AIOHTTP_TIMEOUT) as session:
async with _create_bench_client_session() as session:
output = RequestFuncOutput()
try:
async with session.post(url=api_url) as response:
Expand Down
Loading