Convert benchmarks to ruff format (#18068)

Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
This commit is contained in:
Harry Mellor
2025-05-13 13:43:29 +00:00
committed by GitHub
parent b922c2ebd2
commit 009d9e7590
41 changed files with 3980 additions and 2938 deletions
+41 -34
View File
@@ -11,9 +11,9 @@ from typing import Any, Optional
import numpy as np
import torch
from benchmark_utils import convert_to_pytorch_benchmark_format, write_to_json
from tqdm import tqdm
from benchmark_utils import convert_to_pytorch_benchmark_format, write_to_json
from vllm import LLM, SamplingParams
from vllm.engine.arg_utils import EngineArgs
from vllm.inputs import PromptType
@@ -21,13 +21,14 @@ from vllm.sampling_params import BeamSearchParams
from vllm.utils import FlexibleArgumentParser
def save_to_pytorch_benchmark_format(args: argparse.Namespace,
results: dict[str, Any]) -> None:
def save_to_pytorch_benchmark_format(
args: argparse.Namespace, results: dict[str, Any]
) -> None:
pt_records = convert_to_pytorch_benchmark_format(
args=args,
metrics={"latency": results["latencies"]},
extra_info={k: results[k]
for k in ["avg_latency", "percentiles"]})
extra_info={k: results[k] for k in ["avg_latency", "percentiles"]},
)
if pt_records:
pt_file = f"{os.path.splitext(args.output_json)[0]}.pytorch.json"
write_to_json(pt_file, pt_records)
@@ -42,9 +43,11 @@ def main(args: argparse.Namespace):
# the engine will automatically process the request in multiple batches.
llm = LLM(**dataclasses.asdict(engine_args))
assert llm.llm_engine.model_config.max_model_len >= (
args.input_len +
args.output_len), ("Please ensure that max_model_len is greater than"
" the sum of input_len and output_len.")
args.input_len + args.output_len
), (
"Please ensure that max_model_len is greater than"
" the sum of input_len and output_len."
)
sampling_params = SamplingParams(
n=args.n,
@@ -55,18 +58,16 @@ def main(args: argparse.Namespace):
detokenize=not args.disable_detokenize,
)
print(sampling_params)
dummy_prompt_token_ids = np.random.randint(10000,
size=(args.batch_size,
args.input_len))
dummy_prompts: list[PromptType] = [{
"prompt_token_ids": batch
} for batch in dummy_prompt_token_ids.tolist()]
dummy_prompt_token_ids = np.random.randint(
10000, size=(args.batch_size, args.input_len)
)
dummy_prompts: list[PromptType] = [
{"prompt_token_ids": batch} for batch in dummy_prompt_token_ids.tolist()
]
def llm_generate():
if not args.use_beam_search:
llm.generate(dummy_prompts,
sampling_params=sampling_params,
use_tqdm=False)
llm.generate(dummy_prompts, sampling_params=sampling_params, use_tqdm=False)
else:
llm.beam_search(
dummy_prompts,
@@ -80,12 +81,13 @@ def main(args: argparse.Namespace):
def run_to_completion(profile_dir: Optional[str] = None):
if profile_dir:
with torch.profiler.profile(
activities=[
torch.profiler.ProfilerActivity.CPU,
torch.profiler.ProfilerActivity.CUDA,
],
on_trace_ready=torch.profiler.tensorboard_trace_handler(
str(profile_dir)),
activities=[
torch.profiler.ProfilerActivity.CPU,
torch.profiler.ProfilerActivity.CUDA,
],
on_trace_ready=torch.profiler.tensorboard_trace_handler(
str(profile_dir)
),
) as p:
llm_generate()
print(p.key_averages().table(sort_by="self_cuda_time_total"))
@@ -103,8 +105,9 @@ def main(args: argparse.Namespace):
if args.profile:
profile_dir = args.profile_result_dir
if not profile_dir:
profile_dir = (Path(".") / "vllm_benchmark_result" /
f"latency_result_{time.time()}")
profile_dir = (
Path(".") / "vllm_benchmark_result" / f"latency_result_{time.time()}"
)
print(f"Profiling (results will be saved to '{profile_dir}')...")
run_to_completion(profile_dir=profile_dir)
return
@@ -135,7 +138,8 @@ def main(args: argparse.Namespace):
if __name__ == "__main__":
parser = FlexibleArgumentParser(
description="Benchmark the latency of processing a single batch of "
"requests till completion.")
"requests till completion."
)
parser.add_argument("--input-len", type=int, default=32)
parser.add_argument("--output-len", type=int, default=128)
parser.add_argument("--batch-size", type=int, default=8)
@@ -152,10 +156,9 @@ if __name__ == "__main__":
default=10,
help="Number of iterations to run for warmup.",
)
parser.add_argument("--num-iters",
type=int,
default=30,
help="Number of iterations to run.")
parser.add_argument(
"--num-iters", type=int, default=30, help="Number of iterations to run."
)
parser.add_argument(
"--profile",
action="store_true",
@@ -165,8 +168,10 @@ if __name__ == "__main__":
"--profile-result-dir",
type=str,
default=None,
help=("path to save the pytorch profiler output. Can be visualized "
"with ui.perfetto.dev or Tensorboard."),
help=(
"path to save the pytorch profiler output. Can be visualized "
"with ui.perfetto.dev or Tensorboard."
),
)
parser.add_argument(
"--output-json",
@@ -177,8 +182,10 @@ if __name__ == "__main__":
parser.add_argument(
"--disable-detokenize",
action="store_true",
help=("Do not detokenize responses (i.e. do not include "
"detokenization time in the latency measurement)"),
help=(
"Do not detokenize responses (i.e. do not include "
"detokenization time in the latency measurement)"
),
)
parser = EngineArgs.add_cli_args(parser)