20231088/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

Fix range_ratio Bug in RandomDataset (#16126)

Browse Source 
Signed-off-by: jadewang21 <jadewangcn@outlook.com>
This commit is contained in:
WWW 2025-04-11 06:31:17 +08:00 committed by GitHub
parent 3cc9af88ff
commit 268c325078
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
3 changed files with 42 additions and 20 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

23
benchmarks/benchmark_dataset.py
View File

@ -288,7 +288,7 @@ def process_image(image: Any) -> Mapping[str, Any]:
class RandomDataset(BenchmarkDataset):
# Default values copied from benchmark_serving.py for the random dataset.
DEFAULT_PREFIX_LEN = 0
DEFAULT_RANGE_RATIO = 1.0
DEFAULT_RANGE_RATIO = 0.0
DEFAULT_INPUT_LEN = 1024
DEFAULT_OUTPUT_LEN = 128
@ -308,19 +308,32 @@ class RandomDataset(BenchmarkDataset):
output_len: int = DEFAULT_OUTPUT_LEN,
**kwargs,
) -> list[SampleRequest]:
# Enforce range_ratio < 1
assert range_ratio < 1.0, (
"random_range_ratio must be < 1.0 to ensure a valid sampling range"
)
vocab_size = tokenizer.vocab_size
prefix_token_ids = (np.random.randint(
0, vocab_size, size=prefix_len).tolist() if prefix_len > 0 else [])
input_low = int(input_len * range_ratio)
output_low = int(output_len * range_ratio)
# New sampling logic: [X * (1 - b), X * (1 + b)]
input_low = int(input_len * (1 - range_ratio))
input_high = int(input_len * (1 + range_ratio))
output_low = int(output_len * (1 - range_ratio))
output_high = int(output_len * (1 + range_ratio))
# Add logging for debugging
logger.info("Sampling input_len from [%s, %s]", input_low, input_high)
logger.info("Sampling output_len from [%s, %s]", output_low,
output_high)
input_lens = np.random.randint(input_low,
input_len + 1,
input_high + 1,
size=num_requests)
output_lens = np.random.randint(output_low,
output_len + 1,
output_high + 1,
size=num_requests)
offsets = np.random.randint(0, vocab_size, size=num_requests)

19
benchmarks/benchmark_serving.py
View File

@ -996,18 +996,23 @@ if __name__ == "__main__":
random_group.add_argument(
"--random-range-ratio",
type=float,
default=1.0,
help="Range of sampled ratio of input/output length, "
"used only for random sampling.",
default=0.0,
help="Range ratio for sampling input/output length, "
"used only for random sampling. Must be in the range [0, 1) to define "
"a symmetric sampling range"
"[length * (1 - range_ratio), length * (1 + range_ratio)].",
)
random_group.add_argument(
"--random-prefix-len",
type=int,
default=0,
help="Number of fixed prefix tokens before random "
" context. The length range of context in a random "
" request is [random-prefix-len, "
" random-prefix-len + random-prefix-len * random-range-ratio).")
help=("Number of fixed prefix tokens before the random context "
"in a request. "
"The total input length is the sum of `random-prefix-len` and "
"a random "
"context length sampled from [input_len * (1 - range_ratio), "
"input_len * (1 + range_ratio)]."),
)
hf_group = parser.add_argument_group("hf dataset options")
hf_group.add_argument("--hf-subset",

20
benchmarks/benchmark_throughput.py
View File

@ -594,18 +594,22 @@ if __name__ == "__main__":
default=None,
help="Path to the lora adapters to use. This can be an absolute path, "
"a relative path, or a Hugging Face model identifier.")
parser.add_argument("--prefix-len",
type=int,
default=None,
help="Number of prefix tokens per request."
"This is for the RandomDataset and SonnetDataset")
parser.add_argument(
"--prefix-len",
type=int,
default=0,
help="Number of fixed prefix tokens before the random "
"context in a request (default: 0).",
)
# random dataset
parser.add_argument(
"--random-range-ratio",
type=float,
default=None,
help="Range of sampled ratio of input/output length, "
"used only for RandomDataSet.",
default=0.0,
help="Range ratio for sampling input/output length, "
"used only for RandomDataset. Must be in the range [0, 1) to define "
"a symmetric sampling range "
"[length * (1 - range_ratio), length * (1 + range_ratio)].",
)
# hf dtaset