DeepSeek开源六款华为昇腾项目
DeepSeek开源了TileLang等六款华为昇腾项目，让同一源代码可编译为华为芯片版本，减少对英伟达的依赖。
DeepSeek开源了六款华为昇腾项目，其矩阵内核达到芯片峰值速度的99.8%。主要项目TileLang是DeepSeek编写GPU内核的编程语言，其V4模型的大部分算子都用TileLang编写，现在都有了昇腾版本。DeepGEMM-Ascend实现矩阵乘法，达到431 BFLOPS，接近432的理论上限。
DeepSeek open-sourced six Huawei Ascend projects whose matrix kernels hit 99.8% of the chip's peak speed.
this will help reduce reliance on Nvidia further for them.
The headline project is TileLang, the programming language DeepSeek writes its own GPU kernels in.
Most of the operators that trained its V4 models are written in TileLang, and each now has an Ascend version. That means the same source code can compile for Huawei chips instead of Nvidia ones.
a 2nd repo, DeepGEMM-Ascend, does matrix multiplication and reports 431 BF16 TFLOPS against a 432 ceiling. DeepEP-Ascend, which moves data between chips, shipped with no license file while the rest are MIT, so nobody can legally reuse it yet.
Liang Wenfeng told investors Huawei could start delivering training chips this quarter.
