Improve benchmark scripts (#717)

benchmark/latency_throughput/bench_serving.py

@@ -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)

python/sglang/bench_serving.py

@@ -5,6 +5,9 @@ Benchmark online serving.
 
 Usage:
 python3 -m sglang.bench_serving --backend sglang --num-prompt 10
+
+python3 -m sglang.bench_serving --backend sglang --dataset-name random --num-prompts 3000 --random-input 1024 --random-output 1024 --random-range-ratio 0.5
+python3 -m sglang.bench_serving --backend sglang --dataset-name random --request-rate-range 1,2,4,8,16,32 --random-input 4096 --random-output 1024 --random-range-ratio 0.125 --multi
 """
 
 import argparse

python/sglang/srt/managers/controller/tp_worker.py

@@ -116,13 +116,9 @@ class ModelTpServer:
             f"[gpu_id={self.gpu_id}] "
             f"max_total_num_tokens={self.max_total_num_tokens}, "
             f"max_prefill_tokens={self.max_prefill_tokens}, "
+            f"max_running_requests={self.max_running_requests}, "
             f"context_len={self.model_config.context_len}"
         )
-        if self.tp_rank == 0:
-            logger.info(
-                f"[gpu_id={self.gpu_id}] "
-                f"server_args: {server_args.print_mode_args()}"
-            )
 
         # Init cache
         self.tree_cache = RadixCache(