LoCA enables forward‑only LLM tuning after one‑shot calibration
LoCA replaces repeated back‑propagation with a single probe pass that learns low‑rank correction maps for each transformer block. The method matches or beats LoRA on 16 of 25 benchmarks while cutting GPU peak usage by ~27% and CPU memory and per‑pass time by 40‑50%. It works across Qwen2.5 models from 0.5B to 14B and SmolLM2‑1.7B.