biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

Convert benchmarks to ruff format (#18068)

Browse Source 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
This commit is contained in:
Harry Mellor
2025-05-13 14:43:29 +01:00
committed by GitHub
parent b922c2ebd2
commit 009d9e7590
41 changed files with 3980 additions and 2938 deletions
Download Patch File Download Diff File Expand all files Collapse all files

81
benchmarks/benchmark_long_document_qa_throughput.py
View File

@@ -76,7 +76,7 @@ def repeat_prompts(prompts, repeat_count, mode: str):
- 'random': Shuffle the prompts randomly after repetition.
- 'tile': Repeat the entire prompt list in sequence.
Example: [1, 2, 3] -> [1, 2, 3, 1, 2, 3].
- 'interleave': Repeat each prompt consecutively before moving to
- 'interleave': Repeat each prompt consecutively before moving to
the next. Example: [1, 2, 3] -> [1, 1, 2, 2, 3, 3].
Returns:
@@ -86,20 +86,21 @@ def repeat_prompts(prompts, repeat_count, mode: str):
ValueError: If an invalid mode is provided.
"""
print("Repeat mode: ", mode)
if mode == 'random':
if mode == "random":
repeated_prompts = prompts * repeat_count
random.shuffle(repeated_prompts)
return repeated_prompts
elif mode == 'tile':
elif mode == "tile":
return prompts * repeat_count
elif mode == 'interleave':
elif mode == "interleave":
repeated_prompts = []
for prompt in prompts:
repeated_prompts.extend([prompt] * repeat_count)
return repeated_prompts
else:
raise ValueError(f"Invalid mode: {mode}, only support "
"'random', 'tile', 'interleave'")
raise ValueError(
f"Invalid mode: {mode}, only support 'random', 'tile', 'interleave'"
)
def main(args):
@@ -109,16 +110,16 @@ def main(args):
# we append the document id at the beginning to avoid any of the document
# being the prefix of other documents
prompts = [
str(i) + ' '.join(['hi'] * args.document_length)
str(i) + " ".join(["hi"] * args.document_length)
for i in range(args.num_documents)
]
prompts = repeat_prompts(prompts, args.repeat_count, mode=args.repeat_mode)
warmup_prompts = [
"This is warm up request " + str(i) + \
' '.join(['hi'] * args.document_length)
for i in range(args.num_documents)]
"This is warm up request " + str(i) + " ".join(["hi"] * args.document_length)
for i in range(args.num_documents)
]
# Create the LLM engine
engine_args = EngineArgs.from_cli_args(args)
@@ -142,42 +143,52 @@ def main(args):
if __name__ == "__main__":
parser = FlexibleArgumentParser(
description=
'Benchmark the performance with or without automatic prefix caching.')
description="Benchmark the performance with or "
"without automatic prefix caching."
)
parser.add_argument(
'--document-length',
"--document-length",
type=int,
# Roughly the number of tokens for a system paper,
# excluding images
default=20000,
help='Range of input lengths for sampling prompts,'
'specified as "min:max" (e.g., "128:256").')
help="Range of input lengths for sampling prompts, "
'specified as "min:max" (e.g., "128:256").',
)
parser.add_argument('--num-documents',
type=int,
default=8,
help='Range of input lengths for sampling prompts,'
'specified as "min:max" (e.g., "128:256").')
parser.add_argument(
"--num-documents",
type=int,
default=8,
help="Range of input lengths for sampling prompts, "
'specified as "min:max" (e.g., "128:256").',
)
parser.add_argument('--output-len', type=int, default=10)
parser.add_argument("--output-len", type=int, default=10)
parser.add_argument('--repeat-count',
type=int,
default=2,
help='Number of times to repeat each prompt')
parser.add_argument(
"--repeat-count",
type=int,
default=2,
help="Number of times to repeat each prompt",
)
parser.add_argument("--repeat-mode",
type=str,
default='random',
help='The mode to repeat prompts. The supported '
'modes are "random", "tile", and "interleave". '
'See repeat_prompts() in the source code for details.')
parser.add_argument(
"--repeat-mode",
type=str,
default="random",
help="The mode to repeat prompts. The supported "
'modes are "random", "tile", and "interleave". '
"See repeat_prompts() in the source code for details.",
)
parser.add_argument("--shuffle-seed",
type=int,
default=0,
help='Random seed when the repeat mode is "random"')
parser.add_argument(
"--shuffle-seed",
type=int,
default=0,
help='Random seed when the repeat mode is "random"',
)
parser = EngineArgs.add_cli_args(parser)
args = parser.parse_args()