remove redundant rank0_log function. (#9560)

Co-authored-by: linhuang <linhuang@ruijie.com.cn>

python/sglang/srt/model_executor/cuda_graph_runner.py

@@ -54,7 +54,7 @@ from sglang.srt.utils import (
     empty_context,
     get_available_gpu_memory,
     get_device_memory_capacity,
-    rank0_log,
+    log_info_on_rank0,
     require_attn_tp_gather,
     require_gathered_buffer,
     require_mlp_sync,
@@ -267,7 +267,7 @@ class CudaGraphRunner:
 
         # Batch sizes to capture
         self.capture_bs, self.compile_bs = get_batch_sizes_to_capture(model_runner)
-        rank0_log(f"Capture cuda graph bs {self.capture_bs}")
+        log_info_on_rank0(logger, f"Capture cuda graph bs {self.capture_bs}")
         self.capture_forward_mode = ForwardMode.DECODE
         self.capture_hidden_mode = CaptureHiddenMode.NULL
         self.num_tokens_per_bs = 1

python/sglang/srt/utils.py

@@ -2002,13 +2002,6 @@ def configure_ipv6(dist_init_addr):
     return port, host
 
 
-def rank0_log(msg: str):
-    from sglang.srt.distributed import get_tensor_model_parallel_rank
-
-    if get_tensor_model_parallel_rank() == 0:
-        logger.info(msg)
-
-
 def launch_dummy_health_check_server(host, port, enable_metrics):
     import asyncio