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
+70 -52
View File
@@ -1,5 +1,6 @@
# SPDX-License-Identifier: Apache-2.0
"""Benchmark offline prioritization."""
import argparse
import dataclasses
import json
@@ -13,7 +14,7 @@ from vllm.engine.arg_utils import EngineArgs
from vllm.utils import FlexibleArgumentParser
#Select a equi-probable random priority
# Select a equi-probable random priority
def get_random_flag():
return 0 if random.random() < 0.5 else 1
@@ -33,8 +34,10 @@ def sample_requests(
# Filter out the conversations with less than 2 turns.
dataset = [data for data in dataset if len(data["conversations"]) >= 2]
# Only keep the first two turns of each conversation.
dataset = [(data["conversations"][0]["value"],
data["conversations"][1]["value"]) for data in dataset]
dataset = [
(data["conversations"][0]["value"], data["conversations"][1]["value"])
for data in dataset
]
# Shuffle the dataset.
random.shuffle(dataset)
@@ -51,8 +54,9 @@ def sample_requests(
completion = dataset[i][1]
completion_token_ids = tokenizer(completion).input_ids
prompt_len = len(prompt_token_ids)
output_len = len(completion_token_ids
) if fixed_output_len is None else fixed_output_len
output_len = (
len(completion_token_ids) if fixed_output_len is None else fixed_output_len
)
if prompt_len < 4 or output_len < 4:
# Prune too short sequences.
continue
@@ -74,13 +78,16 @@ def run_vllm(
disable_detokenize: bool = False,
) -> float:
from vllm import LLM, SamplingParams
llm = LLM(**dataclasses.asdict(engine_args))
assert all(
llm.llm_engine.model_config.max_model_len >= (request[1] + request[2])
for request in requests), (
"Please ensure that max_model_len is greater than the sum of"
" input_len and output_len for all requests.")
for request in requests
), (
"Please ensure that max_model_len is greater than the sum of"
" input_len and output_len for all requests."
)
# Add the requests to the engine.
prompts = []
@@ -97,7 +104,8 @@ def run_vllm(
ignore_eos=True,
max_tokens=output_len,
detokenize=not disable_detokenize,
))
)
)
start = time.perf_counter()
llm.generate(prompts, sampling_params, priority=priority, use_tqdm=True)
@@ -111,26 +119,33 @@ def main(args: argparse.Namespace):
# Sample the requests.
tokenizer = AutoTokenizer.from_pretrained(
args.tokenizer, trust_remote_code=args.trust_remote_code)
args.tokenizer, trust_remote_code=args.trust_remote_code
)
if args.dataset is None:
# Synthesize a prompt with the given input length.
prompt = "hi" * (args.input_len - 1)
requests = [(prompt, args.input_len, args.output_len,
get_random_flag()) for _ in range(args.num_prompts)]
requests = [
(prompt, args.input_len, args.output_len, get_random_flag())
for _ in range(args.num_prompts)
]
else:
requests = sample_requests(args.dataset, args.num_prompts, tokenizer,
args.output_len)
requests = sample_requests(
args.dataset, args.num_prompts, tokenizer, args.output_len
)
if args.backend == "vllm":
elapsed_time = run_vllm(requests, args.n,
EngineArgs.from_cli_args(args),
args.disable_detokenize)
elapsed_time = run_vllm(
requests, args.n, EngineArgs.from_cli_args(args), args.disable_detokenize
)
else:
raise ValueError(f"Unknown backend: {args.backend}")
total_num_tokens = sum(prompt_len + output_len
for _, prompt_len, output_len, priority in requests)
print(f"Throughput: {len(requests) / elapsed_time:.2f} requests/s, "
f"{total_num_tokens / elapsed_time:.2f} tokens/s")
total_num_tokens = sum(
prompt_len + output_len for _, prompt_len, output_len, priority in requests
)
print(
f"Throughput: {len(requests) / elapsed_time:.2f} requests/s, "
f"{total_num_tokens / elapsed_time:.2f} tokens/s"
)
# Output JSON results if specified
if args.output_json:
@@ -147,41 +162,44 @@ def main(args: argparse.Namespace):
if __name__ == "__main__":
parser = FlexibleArgumentParser(description="Benchmark the throughput.")
parser.add_argument("--backend",
type=str,
choices=["vllm", "hf", "mii"],
default="vllm")
parser.add_argument("--dataset",
type=str,
default=None,
help="Path to the dataset.")
parser.add_argument("--input-len",
type=int,
default=None,
help="Input prompt length for each request")
parser.add_argument("--output-len",
type=int,
default=None,
help="Output length for each request. Overrides the "
"output length from the dataset.")
parser.add_argument("--n",
type=int,
default=1,
help="Number of generated sequences per prompt.")
parser.add_argument("--num-prompts",
type=int,
default=200,
help="Number of prompts to process.")
parser.add_argument(
'--output-json',
"--backend", type=str, choices=["vllm", "hf", "mii"], default="vllm"
)
parser.add_argument(
"--dataset", type=str, default=None, help="Path to the dataset."
)
parser.add_argument(
"--input-len",
type=int,
default=None,
help="Input prompt length for each request",
)
parser.add_argument(
"--output-len",
type=int,
default=None,
help="Output length for each request. Overrides the "
"output length from the dataset.",
)
parser.add_argument(
"--n", type=int, default=1, help="Number of generated sequences per prompt."
)
parser.add_argument(
"--num-prompts", type=int, default=200, help="Number of prompts to process."
)
parser.add_argument(
"--output-json",
type=str,
default=None,
help='Path to save the throughput results in JSON format.')
help="Path to save the throughput results in JSON format.",
)
parser.add_argument(
'--disable-detokenize',
action='store_true',
help=("Do not detokenize responses (i.e. do not include "
"detokenization time in the latency measurement)"),
"--disable-detokenize",
action="store_true",
help=(
"Do not detokenize responses (i.e. do not include "
"detokenization time in the latency measurement)"
),
)
parser = EngineArgs.add_cli_args(parser)