xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-10 07:45:29 +08:00
Code Issues Packages Projects Releases Wiki Activity

[Benchmark] Parameterization of streaming loading of multimodal datasets (#20528)

Browse Source 
Signed-off-by: wangli <wangli858794774@gmail.com>
This commit is contained in:
Li Wang 2025-07-09 21:35:16 +08:00 committed by GitHub
parent 70ca5484f5
commit 9ff2af6d2b
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
4 changed files with 24 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
benchmarks/benchmark_dataset.py
View File

@ -701,6 +701,7 @@ class HuggingFaceDataset(BenchmarkDataset):
self,
dataset_path: str,
dataset_split: str,
no_stream: bool = False,
dataset_subset: Optional[str] = None,
**kwargs,
) -> None:
@ -708,6 +709,7 @@ class HuggingFaceDataset(BenchmarkDataset):
self.dataset_split = dataset_split
self.dataset_subset = dataset_subset
self.load_stream = not no_stream
self.load_data()
def load_data(self) -> None:
@ -716,7 +718,7 @@ class HuggingFaceDataset(BenchmarkDataset):
self.dataset_path,
name=self.dataset_subset,
split=self.dataset_split,
streaming=True,
streaming=self.load_stream,
)
self.data = self.data.shuffle(seed=self.random_seed)

6
benchmarks/benchmark_serving.py
View File

@ -825,6 +825,7 @@ def main(args: argparse.Namespace):
dataset_subset=args.hf_subset,
dataset_split=args.hf_split,
random_seed=args.seed,
no_stream=args.no_stream,
).sample(
num_requests=args.num_prompts,
tokenizer=tokenizer,
@ -1033,6 +1034,11 @@ def create_argument_parser():
help="Path to the sharegpt/sonnet dataset. "
"Or the huggingface dataset ID if using HF dataset.",
)
parser.add_argument(
"--no-stream",
action="store_true",
help="Do not load the dataset in streaming mode.",
)
parser.add_argument(
"--max-concurrency",
type=int,

6
benchmarks/benchmark_throughput.py
View File

@ -356,6 +356,7 @@ def get_requests(args, tokenizer):
elif args.dataset_name == "burstgpt":
dataset_cls = BurstGPTDataset
elif args.dataset_name == "hf":
common_kwargs["no_stream"] = args.no_stream
if args.dataset_path in VisionArenaDataset.SUPPORTED_DATASET_PATHS:
dataset_cls = VisionArenaDataset
common_kwargs["dataset_subset"] = None
@ -610,6 +611,11 @@ def create_argument_parser():
help="Name of the dataset to benchmark on.",
default="sharegpt",
)
parser.add_argument(
"--no-stream",
action="store_true",
help="Do not load the dataset in streaming mode.",
)
parser.add_argument(
"--dataset",
type=str,

10
vllm/benchmarks/datasets.py
View File

@ -481,6 +481,11 @@ def add_dataset_parser(parser: FlexibleArgumentParser):
choices=["sharegpt", "burstgpt", "sonnet", "random", "hf", "custom"],
help="Name of the dataset to benchmark on.",
)
parser.add_argument(
"--no-stream",
action="store_true",
help="Do not load the dataset in streaming mode.",
)
parser.add_argument(
"--dataset-path",
type=str,
@ -674,6 +679,7 @@ def get_samples(args, tokenizer) -> list[SampleRequest]:
dataset_subset=args.hf_subset,
dataset_split=args.hf_split,
random_seed=args.seed,
no_stream=args.no_stream,
).sample(
num_requests=args.num_prompts,
tokenizer=tokenizer,
@ -971,6 +977,7 @@ class HuggingFaceDataset(BenchmarkDataset):
self,
dataset_path: str,
dataset_split: str,
no_stream: bool = False,
dataset_subset: Optional[str] = None,
**kwargs,
) -> None:
@ -978,6 +985,7 @@ class HuggingFaceDataset(BenchmarkDataset):
self.dataset_split = dataset_split
self.dataset_subset = dataset_subset
self.load_stream = not no_stream
self.load_data()
def load_data(self) -> None:
@ -986,7 +994,7 @@ class HuggingFaceDataset(BenchmarkDataset):
self.dataset_path,
name=self.dataset_subset,
split=self.dataset_split,
streaming=True,
streaming=self.load_stream,
)
self.data = self.data.shuffle(seed=self.random_seed)