From d9a543c500e9014045d7ae769df0ca7782e31870 Mon Sep 17 00:00:00 2001 From: Aditya Ganesh Kumar Date: Tue, 13 Oct 2026 17:31:59 +0530 Subject: [PATCH] [Bugfix][Frontend] Forward --enable-log-outputs to the Cohere Chat v2 (#61089) Signed-off-by: Aditya Ganesh Kumar --- vllm/entrypoints/cohere/serving.py | 4 ++++ vllm/entrypoints/generate/api_router.py | 2 ++ 2 files changed, 6 insertions(+) diff --git a/vllm/entrypoints/cohere/serving.py b/vllm/entrypoints/cohere/serving.py index ec6dd89c3e..93f6d14a3b 100644 --- a/vllm/entrypoints/cohere/serving.py +++ b/vllm/entrypoints/cohere/serving.py @@ -254,6 +254,8 @@ class CohereServingChatV2(OpenAIServingChat): tool_strict_level: str = "auto", enable_prompt_tokens_details: bool = False, enable_force_include_usage: bool = False, + enable_log_outputs: bool = False, + enable_log_deltas: bool = True, default_chat_template_kwargs: dict[str, Any] | None = None, is_reasoning_model: bool = True, ) -> None: @@ -272,6 +274,8 @@ class CohereServingChatV2(OpenAIServingChat): tool_parser=tool_parser, enable_prompt_tokens_details=enable_prompt_tokens_details, enable_force_include_usage=enable_force_include_usage, + enable_log_outputs=enable_log_outputs, + enable_log_deltas=enable_log_deltas, default_chat_template_kwargs=default_chat_template_kwargs, ) # Controls how the assistant's chain-of-thought is surfaced on diff --git a/vllm/entrypoints/generate/api_router.py b/vllm/entrypoints/generate/api_router.py index 9bbe4e879b..942a1c3e78 100644 --- a/vllm/entrypoints/generate/api_router.py +++ b/vllm/entrypoints/generate/api_router.py @@ -208,6 +208,8 @@ async def init_generate_state( reasoning_parser=args.structured_outputs_config.reasoning_parser, enable_prompt_tokens_details=args.enable_prompt_tokens_details, enable_force_include_usage=args.enable_force_include_usage, + enable_log_outputs=args.enable_log_outputs, + enable_log_deltas=args.enable_log_deltas, default_chat_template_kwargs=default_chat_template_kwargs, is_reasoning_model=args.cohere_is_reasoning_model, )