From 7b009aaba5914549acbeee1723e210e8fd7c1e51 Mon Sep 17 00:00:00 2001 From: Radoslav Gerganov Date: Thu, 16 Oct 2025 11:16:10 +0300 Subject: [PATCH] [Feature] Add LlamaCPP as server engine option llama.cpp is exposing OpenAI compatible APIs and works perfectly fine with genai-bench. --- genai_bench/cli/option_groups.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/genai_bench/cli/option_groups.py b/genai_bench/cli/option_groups.py index f8ec4b6..8c6ff69 100644 --- a/genai_bench/cli/option_groups.py +++ b/genai_bench/cli/option_groups.py @@ -357,7 +357,7 @@ def server_options(func): func = click.option( "--server-engine", type=click.Choice( - ["vLLM", "SGLang", "TGI", "cohere-TensorRT", "cohere-vLLM"], + ["vLLM", "SGLang", "TGI", "cohere-TensorRT", "cohere-vLLM", "LlamaCPP"], case_sensitive=True, ), required=False,