EngineX-Hygon/sglang
5
0
Fork 0
Code Issues Pull Requests Actions 7 Projects Releases Wiki Activity

Improve benchmark scripts (#717)

Browse Source
This commit is contained in:
Ying Sheng
2024-07-24 14:44:14 -07:00
committed by GitHub
parent 08a3bd19cc
commit 30d8e130e7
3 changed files with 6 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
benchmark/latency_throughput/bench_serving.py
View File

@@ -248,7 +248,7 @@ def main(args: argparse.Namespace):
random.seed(args.seed)
np.random.seed(args.seed)
api_url = f"http://{args.host}:{args.port}/generate"
api_url = f"{args.host}:{args.port}/generate"
if args.tokenizer.endswith(".json") or args.tokenizer.endswith(".model"):
from sglang.srt.hf_transformers_utils import get_tokenizer
@@ -333,7 +333,7 @@ if __name__ == "__main__":
default="srt",
choices=["vllm", "tgi", "srt", "lightllm", "ginfer"],
)
parser.add_argument("--host", type=str, default="localhost")
parser.add_argument("--host", type=str, default="http://localhost")
parser.add_argument("--port", type=int, default=30000)
parser.add_argument("--dataset", type=str, help="Path to the dataset.")
parser.add_argument("--input-len", type=int, default=2048)