Convert benchmarks to ruff format (#18068)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
This commit is contained in:
@@ -63,8 +63,7 @@ class Request:
|
||||
output_len: int
|
||||
|
||||
|
||||
def sample_tokens(tokenizer: PreTrainedTokenizerBase,
|
||||
length: int) -> list[int]:
|
||||
def sample_tokens(tokenizer: PreTrainedTokenizerBase, length: int) -> list[int]:
|
||||
vocab = tokenizer.get_vocab()
|
||||
all_special_ids = set(tokenizer.all_special_ids)
|
||||
|
||||
@@ -91,8 +90,10 @@ def sample_requests_from_dataset(
|
||||
# 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)
|
||||
@@ -113,8 +114,9 @@ def sample_requests_from_dataset(
|
||||
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 min_len <= prompt_len <= max_len:
|
||||
filtered_requests.append(Request(prompt, prompt_len, output_len))
|
||||
|
||||
@@ -128,27 +130,27 @@ def sample_requests_from_random(
|
||||
fixed_output_len: Optional[int],
|
||||
prefix_len: int,
|
||||
) -> list[Request]:
|
||||
|
||||
requests = []
|
||||
prefix_token_ids = sample_tokens(tokenizer, prefix_len)
|
||||
min_len, max_len = input_length_range
|
||||
|
||||
for i in range(num_requests):
|
||||
unique_part_token_ids = sample_tokens(
|
||||
tokenizer,
|
||||
random.randint(min_len - prefix_len, max_len - prefix_len))
|
||||
tokenizer, random.randint(min_len - prefix_len, max_len - prefix_len)
|
||||
)
|
||||
prompt_token_ids = prefix_token_ids + unique_part_token_ids
|
||||
prompt = tokenizer.decode(prompt_token_ids)
|
||||
prompt_len = len(prompt_token_ids)
|
||||
assert (min_len <= prompt_len <= max_len
|
||||
), f"prompt_len {prompt_len} out of range {min_len}:{max_len}"
|
||||
assert min_len <= prompt_len <= max_len, (
|
||||
f"prompt_len {prompt_len} out of range {min_len}:{max_len}"
|
||||
)
|
||||
requests.append(Request(prompt, prompt_len, fixed_output_len))
|
||||
return requests
|
||||
|
||||
|
||||
def repeat_and_sort_requests(requests: list[Request],
|
||||
repeat_count: int,
|
||||
sort: bool = False) -> list[str]:
|
||||
def repeat_and_sort_requests(
|
||||
requests: list[Request], repeat_count: int, sort: bool = False
|
||||
) -> list[str]:
|
||||
repeated_requests = requests * repeat_count
|
||||
if sort:
|
||||
repeated_requests.sort(key=lambda x: x[1])
|
||||
@@ -159,14 +161,14 @@ def repeat_and_sort_requests(requests: list[Request],
|
||||
|
||||
def main(args):
|
||||
tokenizer = get_tokenizer(args.model, trust_remote_code=True)
|
||||
input_length_range = tuple(map(int, args.input_length_range.split(':')))
|
||||
input_length_range = tuple(map(int, args.input_length_range.split(":")))
|
||||
random.seed(args.seed)
|
||||
if args.dataset_path is not None:
|
||||
if args.prefix_len > 0:
|
||||
raise ValueError("prefix-len is not supported when "
|
||||
"dataset-path is provided.")
|
||||
print(f"Start to sample {args.num_prompts} prompts "
|
||||
f"from {args.dataset_path}")
|
||||
raise ValueError(
|
||||
"prefix-len is not supported when dataset-path is provided."
|
||||
)
|
||||
print(f"Start to sample {args.num_prompts} prompts from {args.dataset_path}")
|
||||
filtered_requests = sample_requests_from_dataset(
|
||||
dataset_path=args.dataset_path,
|
||||
num_requests=args.num_prompts,
|
||||
@@ -196,14 +198,16 @@ def main(args):
|
||||
|
||||
llm = LLM(**dataclasses.asdict(engine_args))
|
||||
|
||||
sampling_params = SamplingParams(temperature=0,
|
||||
max_tokens=args.output_len,
|
||||
detokenize=not args.disable_detokenize)
|
||||
sampling_params = SamplingParams(
|
||||
temperature=0,
|
||||
max_tokens=args.output_len,
|
||||
detokenize=not args.disable_detokenize,
|
||||
)
|
||||
|
||||
print("Testing filtered requests")
|
||||
prompts = repeat_and_sort_requests(filtered_requests,
|
||||
repeat_count=args.repeat_count,
|
||||
sort=args.sort)
|
||||
prompts = repeat_and_sort_requests(
|
||||
filtered_requests, repeat_count=args.repeat_count, sort=args.sort
|
||||
)
|
||||
|
||||
print("------start generating------")
|
||||
test_prefix(
|
||||
@@ -215,29 +219,35 @@ def main(args):
|
||||
|
||||
if __name__ == "__main__":
|
||||
parser = FlexibleArgumentParser(
|
||||
description=
|
||||
'Benchmark the performance with or without automatic prefix caching.')
|
||||
parser.add_argument("--dataset-path",
|
||||
type=str,
|
||||
default=None,
|
||||
help="Path to the dataset.")
|
||||
parser.add_argument('--output-len', type=int, default=10)
|
||||
parser.add_argument('--num-prompts',
|
||||
type=int,
|
||||
required=True,
|
||||
help="Number of the prompts sampled from dataset")
|
||||
parser.add_argument('--repeat-count',
|
||||
type=int,
|
||||
default=1,
|
||||
help='Number of times to repeat each prompt')
|
||||
parser.add_argument('--sort',
|
||||
action='store_true',
|
||||
help='Sort prompts by input length')
|
||||
parser.add_argument('--input-length-range',
|
||||
type=str,
|
||||
required=True,
|
||||
help='Range of input lengths for sampling prompts,'
|
||||
'specified as "min:max" (e.g., "128:256").')
|
||||
description="Benchmark the performance with or without "
|
||||
"automatic prefix caching."
|
||||
)
|
||||
parser.add_argument(
|
||||
"--dataset-path", type=str, default=None, help="Path to the dataset."
|
||||
)
|
||||
parser.add_argument("--output-len", type=int, default=10)
|
||||
parser.add_argument(
|
||||
"--num-prompts",
|
||||
type=int,
|
||||
required=True,
|
||||
help="Number of the prompts sampled from dataset",
|
||||
)
|
||||
parser.add_argument(
|
||||
"--repeat-count",
|
||||
type=int,
|
||||
default=1,
|
||||
help="Number of times to repeat each prompt",
|
||||
)
|
||||
parser.add_argument(
|
||||
"--sort", action="store_true", help="Sort prompts by input length"
|
||||
)
|
||||
parser.add_argument(
|
||||
"--input-length-range",
|
||||
type=str,
|
||||
required=True,
|
||||
help="Range of input lengths for sampling prompts,"
|
||||
'specified as "min:max" (e.g., "128:256").',
|
||||
)
|
||||
parser.add_argument(
|
||||
"--prefix-len",
|
||||
type=int,
|
||||
@@ -248,10 +258,12 @@ if __name__ == "__main__":
|
||||
"when dataset-path is not provided.",
|
||||
)
|
||||
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)
|
||||
|
||||
Reference in New Issue
Block a user