[CI] Fix ci tests (#5769)

python/sglang/bench_one_batch.py

@@ -57,6 +57,7 @@ import torch
 import torch.distributed as dist
 
 from sglang.srt.configs.model_config import ModelConfig
+from sglang.srt.distributed.parallel_state import destroy_distributed_environment
 from sglang.srt.entrypoints.engine import _set_envs_and_config
 from sglang.srt.hf_transformers_utils import get_tokenizer
 from sglang.srt.managers.schedule_batch import Req, ScheduleBatch
@@ -502,8 +503,13 @@ def latency_test(
             for result in result_list:
                 fout.write(json.dumps(result) + "\n")
 
+    if server_args.tp_size > 1:
+        destroy_distributed_environment()
+
 
 def main(server_args, bench_args):
+    server_args.cuda_graph_max_bs = max(bench_args.batch_size)
+
     _set_envs_and_config(server_args)
 
     if server_args.model_path: