From b9dcbc199fb3966ee1d0f6060d1cb80d65888ee2 Mon Sep 17 00:00:00 2001 From: Vuong Hoang Date: Sat, 27 Jun 2026 09:40:47 -0700 Subject: [PATCH] litellm(granite): revert temperature 0.1 -> 0 (research-dictated) dvalin evidence pass: IBM canonical is temp 0; greedy-loop risk is an open-ended-generation phenomenon, not summ/classify; temp 0.1 reduces classification reproducibility without fixing loops (use repetition/presence penalty if loops appear). image-judge stays 0 (Qwen judge card + W&B judge practice = temp 0 for reproducibility; NVFP4-needs-0.1 unsupported). Both gateway temps now 0, vendor-canonical. --- stacks/litellm/conf/config.yaml | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/stacks/litellm/conf/config.yaml b/stacks/litellm/conf/config.yaml index 6b18e79..c5e0888 100644 --- a/stacks/litellm/conf/config.yaml +++ b/stacks/litellm/conf/config.yaml @@ -27,7 +27,7 @@ model_list: model: hosted_vllm/granite-4.1-8b api_base: http://10.250.50.54:8004/v1 api_key: os.environ/VLLM_API_KEY - temperature: 0.1 + temperature: 0 model_info: mode: chat @@ -39,7 +39,7 @@ model_list: model: hosted_vllm/granite-4.1-8b api_base: http://10.250.50.54:8004/v1 api_key: os.environ/VLLM_API_KEY - temperature: 0.1 + temperature: 0 model_info: mode: chat @@ -50,7 +50,7 @@ model_list: model: hosted_vllm/granite-4.1-8b api_base: http://10.250.50.54:8004/v1 api_key: os.environ/VLLM_API_KEY - temperature: 0.1 + temperature: 0 model_info: mode: chat