[Frontend][OpenAI] Support for returning max_model_len on /v1/models response (#4643)

2024-06-02 13:36:13 +05:30
parent ed59a7ed23
commit f790ad3c50
2 changed files with 2 additions and 0 deletions
--- a/vllm/entrypoints/openai/serving_engine.py
+++ b/vllm/entrypoints/openai/serving_engine.py
@@ -62,6 +62,7 @@ class OpenAIServing:
        """Show available models. Right now we only have one model."""
        model_cards = [
            ModelCard(id=served_model_name,
+                      max_model_len=self.max_model_len,
                      root=self.served_model_names[0],
                      permission=[ModelPermission()])
            for served_model_name in self.served_model_names