youngkingdom/vllm
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

[Misc] Add request_id into benchmark_serve.py (#23065)

Browse Source 
Signed-off-by: yangxia <yangxiast@gmail.com>
This commit is contained in:
hustxiayang
2025-08-19 04:32:18 -04:00
committed by GitHub
parent 4efd43e9b4
commit 31436e8b4f
6 changed files with 243 additions and 46 deletions
Download Patch File Download Diff File Expand all files Collapse all files

23
benchmarks/benchmark_serving.py
View File

@ -375,11 +375,12 @@ async def benchmark(
rps_change_events.append({"rps": rps_val, "timestamp": timestamp})
last_int_rps = current_int_rps
prompt, prompt_len, output_len, mm_content = (
prompt, prompt_len, output_len, mm_content, request_id = (
request.prompt,
request.prompt_len,
request.expected_output_len,
request.multi_modal_data,
request.request_id,
)
req_model_id, req_model_name = model_id, model_name
if lora_modules:
@ -397,6 +398,7 @@ async def benchmark(
multi_modal_content=mm_content,
ignore_eos=ignore_eos,
extra_body=extra_body,
request_id=request_id,
)
task = limited_request_func(request_func_input=request_func_input, pbar=pbar)
tasks.append(asyncio.create_task(task))
@ -665,6 +667,7 @@ def main(args: argparse.Namespace):
tokenizer=tokenizer,
output_len=args.custom_output_len,
skip_chat_template=args.custom_skip_chat_template,
request_id_prefix=args.request_id_prefix,
)
elif args.dataset_name == "sonnet":
@ -678,6 +681,7 @@ def main(args: argparse.Namespace):
prefix_len=args.sonnet_prefix_len,
tokenizer=tokenizer,
return_prompt_formatted=False,
request_id_prefix=args.request_id_prefix,
)
else:
assert tokenizer.chat_template or tokenizer.default_chat_template, (
@ -690,6 +694,7 @@ def main(args: argparse.Namespace):
prefix_len=args.sonnet_prefix_len,
tokenizer=tokenizer,
return_prompt_formatted=True,
request_id_prefix=args.request_id_prefix,
)
elif args.dataset_name == "hf":
@ -751,6 +756,7 @@ def main(args: argparse.Namespace):
num_requests=args.num_prompts,
tokenizer=tokenizer,
output_len=args.hf_output_len,
request_id_prefix=args.request_id_prefix,
)
else:
@ -762,10 +768,15 @@ def main(args: argparse.Namespace):
tokenizer=tokenizer,
num_requests=args.num_prompts,
output_len=args.sharegpt_output_len,
request_id_prefix=args.request_id_prefix,
),
"burstgpt": lambda: BurstGPTDataset(
random_seed=args.seed, dataset_path=args.dataset_path
).sample(tokenizer=tokenizer, num_requests=args.num_prompts),
).sample(
tokenizer=tokenizer,
num_requests=args.num_prompts,
request_id_prefix=args.request_id_prefix,
),
"random": lambda: RandomDataset(dataset_path=args.dataset_path).sample(
tokenizer=tokenizer,
num_requests=args.num_prompts,
@ -773,6 +784,7 @@ def main(args: argparse.Namespace):
input_len=args.random_input_len,
output_len=args.random_output_len,
range_ratio=args.random_range_ratio,
request_id_prefix=args.request_id_prefix,
),
}
@ -1118,6 +1130,13 @@ def create_argument_parser():
"goodput, refer to DistServe paper: https://arxiv.org/pdf/2401.09670 "
"and the blog: https://hao-ai-lab.github.io/blogs/distserve",
)
parser.add_argument(
"--request-id-prefix",
type=str,
required=False,
default="benchmark-serving",
help="Specify the prefix of request id.",
)
# group for dataset specific arguments
custom_group = parser.add_argument_group("custom dataset options")