The whole point of OpenAI's Responses API is to help them hide reasoning tracesseangoedecke.com3 points·by Muhtasham·10 เดือนที่ผ่านมา·0 comments
Muhtasham·2 ปีที่แล้ว·discussThanks for detailed analysis, would be curios to see FP8 comparison too, given vllm has some custom kernels