Improve docs and warnings (#1164)

2024-08-20 08:31:29 -07:00
parent d8476818ef
commit a8ae640328
7 changed files with 25 additions and 24 deletions
--- a/python/sglang/srt/model_executor/model_runner.py
+++ b/python/sglang/srt/model_executor/model_runner.py
@@ -237,7 +237,7 @@ class ModelRunner:
        self.max_total_num_tokens = self.profile_max_num_token(total_gpu_memory)
        if max_total_tokens is not None:
            if max_total_tokens > self.max_total_num_tokens:
-                warnings.warn(
+                logging.warning(
                    f"max_total_tokens={max_total_tokens} is larger than the profiled value "
                    f"{self.max_total_num_tokens}. "
                    f"Use the profiled value instead."