Rohan Paul (@rohanpaul_ai)T2·Models
78 pts
An NVIDIA paper proposes compiling an LLM's reasoning trace into small parameterized Python functions that run on CPU, invoking a fine-tuned 1B model only for lightweight text tasks such as value extraction. The cache matched or beat the source model on 7 of 8 math and science benchmarks, scoring 93.3% versus 83.3% on AIME '25, and covered at least 90% of rephrased or re-numbered variants at 16x to 291x lower cost.