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

[bugfix] fix profile impact benchmark results (#21507)

Browse Source 
Signed-off-by: rongfu.leng <rongfu.leng@daocloud.io>
This commit is contained in:
rongfu.leng 2025-07-28 13:44:24 +08:00 committed by GitHub
parent 7656cf4cf3
commit 18cc33dd60
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
3 changed files with 41 additions and 42 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

28
benchmarks/benchmark_serving.py
View File

@ -396,20 +396,6 @@ async def benchmark(
tasks.append(asyncio.create_task(task)) tasks.append(asyncio.create_task(task))
outputs: list[RequestFuncOutput] = await asyncio.gather(*tasks) 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: if pbar is not None:
pbar.close() pbar.close()
@ -518,6 +504,20 @@ async def benchmark(
print("=" * 50) 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 return result

28
benchmarks/benchmark_serving_structured_output.py
View File

@ -538,20 +538,6 @@ async def benchmark(
) )
outputs: list[RequestFuncOutput] = await asyncio.gather(*tasks) 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: if pbar is not None:
pbar.close() pbar.close()
@ -666,6 +652,20 @@ async def benchmark(
print("=" * 50) 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 return result, ret

27
vllm/benchmarks/serve.py
View File

@ -470,20 +470,6 @@ async def benchmark(
pbar=pbar))) pbar=pbar)))
outputs: list[RequestFuncOutput] = await asyncio.gather(*tasks) 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: if pbar is not None:
pbar.close() pbar.close()
@ -576,6 +562,19 @@ async def benchmark(
print("=" * 50) 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 return result