[Misc][Doc] Add note regarding loading generation_config by default (#15281)

Signed-off-by: Roger Wang <ywang@roblox.com>
2025-03-23 14:00:55 -07:00
parent d6cd59f122
commit 9c5c81b0da
4 changed files with 27 additions and 1 deletions
--- a/vllm/config.py
+++ b/vllm/config.py
@@ -1023,6 +1023,13 @@ class ModelConfig:
                    "max_new_tokens")
        else:
            diff_sampling_param = {}
+
+        if diff_sampling_param:
+            logger.warning_once(
+                "Default sampling parameters have been overridden by the "
+                "model's Hugging Face generation config recommended from the "
+                "model creator. If this is not intended, please relaunch "
+                "vLLM instance with `--generation-config vllm`.")
        return diff_sampling_param

    @property