LIMO: Less Is More for Reasoning

Re:LIMO: Less Is More for Reasoning by rfoo on Monday February 10, 2025 @06:51AM (#42999260)

I know that, I'm in this game. I was comparing API throughput/ttft/ttbt of DeekSeek's own R1 API before it went viral in the West, and o3-mini.

I remain unconvinced that DeepSeek themselves didn't optimize their own V3 inference good enough and left another 2x~3x improvement on the table.

[ Parent | on HN ]

Re:LIMO: Less Is More for Reasoning by pama on Monday February 10, 2025 @07:22AM (#42999453)

I am sure DeepSeek did optimize the inference cost of R1. They did not yet release an efficient MoE downscaling of it, ie an R1-mini.

[ Parent | on HN ]