xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-10 06:35:00 +08:00
Code Issues Packages Projects Releases Wiki Activity

[benchmarks]allow skip ready check for bench serve (#25420)

Browse Source 
Signed-off-by: Lu Fang <fanglu@fb.com>
Signed-off-by: Lucia Fang <116399278+luccafong@users.noreply.github.com>
Co-authored-by: Lucia (Lu) Fang <fanglu@meta.com>
This commit is contained in:
Lucia Fang 2025-09-22 20:21:48 -07:00 committed by GitHub
parent f225ea7dd9
commit eea1783989
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 17 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
vllm/benchmarks/serve.py
View File

@ -531,6 +531,7 @@ async def benchmark(
extra_body=extra_body,
)
if ready_check_timeout_sec > 0:
test_output = await wait_for_endpoint(
request_func,
test_input,
@ -539,10 +540,13 @@ async def benchmark(
)
if not test_output.success:
raise ValueError(
"Initial test run failed - Please make sure benchmark arguments "
f"are correctly specified. Error: {test_output.error}")
"Initial test run failed - Please make sure benchmark "
"arguments are correctly specified. "
f"Error: {test_output.error}")
else:
print("Initial test run completed. Starting main benchmark run...")
else:
print("Skipping endpoint ready check.")
if lora_modules:
# For each input request, choose a LoRA module at random.
@ -1151,7 +1155,8 @@ def add_cli_args(parser: argparse.ArgumentParser):
type=int,
default=600,
help="Maximum time to wait for the endpoint to become ready "
"in seconds (default: 600 seconds / 10 minutes).",
"in seconds (default: 600 seconds / 10 minutes). If set to 0, "
"the ready check will be skipped."
)