[Misc][OpenAI] deprecate max_tokens in favor of new max_completion_tokens field for chat completion endpoint (#9837)

2024-10-31 02:15:56 +01:00
parent 64384bbcdf
commit abbfb6134d
14 changed files with 140 additions and 118 deletions
--- a/benchmarks/backend_request_func.py
+++ b/benchmarks/backend_request_func.py
@@ -324,7 +324,7 @@ async def async_request_openai_chat_completions(
                },
            ],
            "temperature": 0.0,
-            "max_tokens": request_func_input.output_len,
+            "max_completion_tokens": request_func_input.output_len,
            "stream": True,
            "ignore_eos": request_func_input.ignore_eos,
        }