mirror of
https://git.datalinker.icu/vllm-project/vllm.git
synced 2025-12-10 00:45:01 +08:00
[Misc]Add param max-model-len in benchmark_latency.py (#5629)
This commit is contained in:
parent
7d46c8d378
commit
d8714530d1
@ -29,6 +29,7 @@ def main(args: argparse.Namespace):
|
||||
tensor_parallel_size=args.tensor_parallel_size,
|
||||
trust_remote_code=args.trust_remote_code,
|
||||
dtype=args.dtype,
|
||||
max_model_len=args.max_model_len,
|
||||
enforce_eager=args.enforce_eager,
|
||||
kv_cache_dtype=args.kv_cache_dtype,
|
||||
quantization_param_path=args.quantization_param_path,
|
||||
@ -150,6 +151,12 @@ if __name__ == '__main__':
|
||||
parser.add_argument('--trust-remote-code',
|
||||
action='store_true',
|
||||
help='trust remote code from huggingface')
|
||||
parser.add_argument(
|
||||
'--max-model-len',
|
||||
type=int,
|
||||
default=None,
|
||||
help='Maximum length of a sequence (including prompt and output). '
|
||||
'If None, will be derived from the model.')
|
||||
parser.add_argument(
|
||||
'--dtype',
|
||||
type=str,
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user