https://douyixuan.github.io/tags/surrogate-model/Recent content in Surrogate-Model on 兜忆轩 | Cedric's Compiler Noteshttps://douyixuan.github.io/images/papermod-cover.pnghttps://douyixuan.github.io/images/papermod-cover.pngHugo -- 0.146.0en-usSun, 27 Sep 2026 12:45:00 +0800https://douyixuan.github.io/posts/ai-silicon-papers/2026-09-27/Sun, 27 Sep 2026 12:45:00 +0800https://douyixuan.github.io/posts/ai-silicon-papers/2026-09-27/GPU Forecasters 让 LLM 预测候选 kernel 相对参考实现的性能分布，再把有限的真实 GPU 测量留给更值得验证的候选；实验说明排序信号有用，也显示校准、分布变化与总成本仍是关键边界。