Skip to content
GitLab
Menu
Projects
Groups
Snippets
Loading...
Help
Help
Support
Community forum
Keyboard shortcuts
?
Submit feedback
Contribute to GitLab
Sign in
Toggle navigation
Menu
Open sidebar
OpenDAS
vllm_cscc
Commits
18cc33dd
Unverified
Commit
18cc33dd
authored
Jul 28, 2025
by
rongfu.leng
Committed by
GitHub
Jul 27, 2025
Browse files
[bugfix] fix profile impact benchmark results (#21507)
Signed-off-by:
rongfu.leng
<
rongfu.leng@daocloud.io
>
parent
7656cf4c
Changes
3
Hide whitespace changes
Inline
Side-by-side
Showing
3 changed files
with
41 additions
and
42 deletions
+41
-42
benchmarks/benchmark_serving.py
benchmarks/benchmark_serving.py
+14
-14
benchmarks/benchmark_serving_structured_output.py
benchmarks/benchmark_serving_structured_output.py
+14
-14
vllm/benchmarks/serve.py
vllm/benchmarks/serve.py
+13
-14
No files found.
benchmarks/benchmark_serving.py
View file @
18cc33dd
...
...
@@ -396,20 +396,6 @@ async def benchmark(
tasks
.
append
(
asyncio
.
create_task
(
task
))
outputs
:
list
[
RequestFuncOutput
]
=
await
asyncio
.
gather
(
*
tasks
)
if
profile
:
print
(
"Stopping profiler..."
)
profile_input
=
RequestFuncInput
(
model
=
model_id
,
prompt
=
test_prompt
,
api_url
=
base_url
+
"/stop_profile"
,
prompt_len
=
test_prompt_len
,
output_len
=
test_output_len
,
logprobs
=
logprobs
,
)
profile_output
=
await
request_func
(
request_func_input
=
profile_input
)
if
profile_output
.
success
:
print
(
"Profiler stopped"
)
if
pbar
is
not
None
:
pbar
.
close
()
...
...
@@ -518,6 +504,20 @@ async def benchmark(
print
(
"="
*
50
)
if
profile
:
print
(
"Stopping profiler..."
)
profile_input
=
RequestFuncInput
(
model
=
model_id
,
prompt
=
test_prompt
,
api_url
=
base_url
+
"/stop_profile"
,
prompt_len
=
test_prompt_len
,
output_len
=
test_output_len
,
logprobs
=
logprobs
,
)
profile_output
=
await
request_func
(
request_func_input
=
profile_input
)
if
profile_output
.
success
:
print
(
"Profiler stopped"
)
return
result
...
...
benchmarks/benchmark_serving_structured_output.py
View file @
18cc33dd
...
...
@@ -538,20 +538,6 @@ async def benchmark(
)
outputs
:
list
[
RequestFuncOutput
]
=
await
asyncio
.
gather
(
*
tasks
)
if
profile
:
print
(
"Stopping profiler..."
)
profile_input
=
RequestFuncInput
(
model
=
model_id
,
prompt
=
test_request
.
prompt
,
api_url
=
base_url
+
"/stop_profile"
,
prompt_len
=
test_request
.
prompt_len
,
output_len
=
test_request
.
expected_output_len
,
extra_body
=
{
test_request
.
structure_type
:
test_request
.
schema
},
)
profile_output
=
await
request_func
(
request_func_input
=
profile_input
)
if
profile_output
.
success
:
print
(
"Profiler stopped"
)
if
pbar
is
not
None
:
pbar
.
close
()
...
...
@@ -666,6 +652,20 @@ async def benchmark(
print
(
"="
*
50
)
if
profile
:
print
(
"Stopping profiler..."
)
profile_input
=
RequestFuncInput
(
model
=
model_id
,
prompt
=
test_request
.
prompt
,
api_url
=
base_url
+
"/stop_profile"
,
prompt_len
=
test_request
.
prompt_len
,
output_len
=
test_request
.
expected_output_len
,
extra_body
=
{
test_request
.
structure_type
:
test_request
.
schema
},
)
profile_output
=
await
request_func
(
request_func_input
=
profile_input
)
if
profile_output
.
success
:
print
(
"Profiler stopped"
)
return
result
,
ret
...
...
vllm/benchmarks/serve.py
View file @
18cc33dd
...
...
@@ -470,20 +470,6 @@ async def benchmark(
pbar
=
pbar
)))
outputs
:
list
[
RequestFuncOutput
]
=
await
asyncio
.
gather
(
*
tasks
)
if
profile
:
print
(
"Stopping profiler..."
)
profile_input
=
RequestFuncInput
(
model
=
model_id
,
prompt
=
test_prompt
,
api_url
=
base_url
+
"/stop_profile"
,
prompt_len
=
test_prompt_len
,
output_len
=
test_output_len
,
logprobs
=
logprobs
,
)
profile_output
=
await
request_func
(
request_func_input
=
profile_input
)
if
profile_output
.
success
:
print
(
"Profiler stopped"
)
if
pbar
is
not
None
:
pbar
.
close
()
...
...
@@ -576,6 +562,19 @@ async def benchmark(
print
(
"="
*
50
)
if
profile
:
print
(
"Stopping profiler..."
)
profile_input
=
RequestFuncInput
(
model
=
model_id
,
prompt
=
test_prompt
,
api_url
=
base_url
+
"/stop_profile"
,
prompt_len
=
test_prompt_len
,
output_len
=
test_output_len
,
logprobs
=
logprobs
,
)
profile_output
=
await
request_func
(
request_func_input
=
profile_input
)
if
profile_output
.
success
:
print
(
"Profiler stopped"
)
return
result
...
...
Write
Preview
Markdown
is supported
0%
Try again
or
attach a new file
.
Attach a file
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment