<![CDATA[newBorn_1991的博客]]>

<![CDATA[newBorn_1991的博客]]>https://blog.csdn.net/newBorn_1991zh-cnhttps://blog.csdn.net/<![CDATA[ops-cv NMS后处理硬件排序单元调用与阈值优化实战]]>https://blog.csdn.net/newBorn_1991/article/details/157834966https://blog.csdn.net/newBorn_1991/article/details/157834966newBorn_1991Sat, 07 Feb 2026 07:16:32 +0800<![CDATA[ops-transformer RoPE位置编码复数旋转硬件加速实战]]>https://blog.csdn.net/newBorn_1991/article/details/157834860https://blog.csdn.net/newBorn_1991/article/details/157834860newBorn_1991Sat, 07 Feb 2026 07:12:29 +0800<![CDATA[图调试工具中间张量导出与精度比对实战]]>https://blog.csdn.net/newBorn_1991/article/details/157812626https://blog.csdn.net/newBorn_1991/article/details/157812626newBorn_1991Fri, 06 Feb 2026 21:00:21 +0800<![CDATA[Triton GE Backend推理引擎集成实战解析]]>https://blog.csdn.net/newBorn_1991/article/details/157812561https://blog.csdn.net/newBorn_1991/article/details/157812561newBorn_1991Fri, 06 Feb 2026 20:57:02 +0800<![CDATA[庖丁解牛：使用Aclnn接口调用一个算子的完整生命周期]]>https://blog.csdn.net/newBorn_1991/article/details/155992818https://blog.csdn.net/newBorn_1991/article/details/155992818newBorn_1991Wed, 17 Dec 2025 13:58:23 +0800<![CDATA[矢量计算的交响乐：Ascend C向量编程范式与指令级并行优化]]>https://blog.csdn.net/newBorn_1991/article/details/155992777https://blog.csdn.net/newBorn_1991/article/details/155992777newBorn_1991Tue, 16 Dec 2025 23:32:28 +0800<![CDATA[驾驭昇腾CANN异步流水线从算子优化到系统级性能跃迁]]>https://blog.csdn.net/newBorn_1991/article/details/155861298https://blog.csdn.net/newBorn_1991/article/details/155861298newBorn_1991Fri, 12 Dec 2025 20:13:14 +0800<![CDATA[使用Python DSL定义与生成昇腾融合算子的艺术]]>https://blog.csdn.net/newBorn_1991/article/details/155858281https://blog.csdn.net/newBorn_1991/article/details/155858281newBorn_1991Fri, 12 Dec 2025 16:05:57 +0800<![CDATA[Ascend C 未来展望：从显式并行到AI原生编程的演进之路]]>https://blog.csdn.net/newBorn_1991/article/details/155705888https://blog.csdn.net/newBorn_1991/article/details/155705888newBorn_1991Mon, 08 Dec 2025 14:35:12 +0800<![CDATA[Pybind调用入门 - 为何它是连接C++算子与Python世界的桥梁？]]>https://blog.csdn.net/newBorn_1991/article/details/155646808https://blog.csdn.net/newBorn_1991/article/details/155646808newBorn_1991Sat, 06 Dec 2025 20:26:40 +0800<![CDATA[构建高性能Ascend C Element-Wise算子 — 从核函数设计到深度优化]]>https://blog.csdn.net/newBorn_1991/article/details/155646692https://blog.csdn.net/newBorn_1991/article/details/155646692newBorn_1991Sat, 06 Dec 2025 20:05:49 +0800<![CDATA[AsNumpy 在高校 AI 教学中的实践 - 开源赋能下一代AI人才]]>https://blog.csdn.net/newBorn_1991/article/details/155577760https://blog.csdn.net/newBorn_1991/article/details/155577760newBorn_1991Fri, 05 Dec 2025 11:22:44 +0800<![CDATA[超越MoeGatingTopK - Ascend C在Transformer架构中的其他融合算子实践]]>https://blog.csdn.net/newBorn_1991/article/details/155577321https://blog.csdn.net/newBorn_1991/article/details/155577321newBorn_1991Thu, 04 Dec 2025 18:54:28 +0800<![CDATA[Ascend C算子开发入门：从AddCustom到Sigmoid的代码实现与思想升华]]>https://blog.csdn.net/newBorn_1991/article/details/155538450https://blog.csdn.net/newBorn_1991/article/details/155538450newBorn_1991Wed, 03 Dec 2025 19:25:13 +0800<![CDATA[Ascend C性能优化深度探秘：Double Buffer与AtomicAdd的实战应用]]>https://blog.csdn.net/newBorn_1991/article/details/155538398https://blog.csdn.net/newBorn_1991/article/details/155538398newBorn_1991Wed, 03 Dec 2025 18:57:36 +0800<![CDATA[Triton - Ascend算子性能优化实战：从架构原理到企业级优化]]>https://blog.csdn.net/newBorn_1991/article/details/155497139https://blog.csdn.net/newBorn_1991/article/details/155497139newBorn_1991Tue, 02 Dec 2025 17:41:09 +0800<![CDATA[性能瓶颈诊断与优化 - Triton-on-Ascend算子调试与性能分析实战]]>https://blog.csdn.net/newBorn_1991/article/details/155496687https://blog.csdn.net/newBorn_1991/article/details/155496687newBorn_1991Tue, 02 Dec 2025 15:27:16 +0800<![CDATA[Ascend C双页表技术详解 - 虚拟地址映射与NPU并行搬运优化]]>https://blog.csdn.net/newBorn_1991/article/details/155458165https://blog.csdn.net/newBorn_1991/article/details/155458165newBorn_1991Mon, 01 Dec 2025 18:21:52 +0800<![CDATA[Ascend C实现Pow算子——Kernel核函数实现]]>https://blog.csdn.net/newBorn_1991/article/details/155457978https://blog.csdn.net/newBorn_1991/article/details/155457978newBorn_1991Mon, 01 Dec 2025 18:17:29 +0800<![CDATA[Ascend C算子开发范式演进：从基础实现到高性能优化的工程哲学]]>https://blog.csdn.net/newBorn_1991/article/details/155392859https://blog.csdn.net/newBorn_1991/article/details/155392859newBorn_1991Sat, 29 Nov 2025 18:23:26 +0800