https://douyixuan.github.io/tags/gpu-kernel/Recent content in Gpu-Kernel 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-usWed, 26 Aug 2026 08:00:00 +0800https://douyixuan.github.io/posts/ai-native/2026-08-26/Wed, 26 Aug 2026 08:00:00 +0800https://douyixuan.github.io/posts/ai-native/2026-08-26/今天两篇都偏生产级 Agent 系统：NVIDIA AVO 展示 persistent memory、supervisor 和 grounded feedback 如何把 frontier model 变成长周期自治 harness，并已用于 Blackwell GPU kernel 优化；Databricks AI SRE 则展示如何把 incident debugging 拆成可组合的 agentic runbook、确定性检查和证据可追溯的 context layer。