DeepSeek and Huawei release open-source Ascend AI programming tools to reduce reliance on Nvidia ecosystem

Chinese AI company DeepSeek has released open-source programming tools developed in partnership with Huawei, for the company's Ascend AI chips, as part of efforts to reduce reliance on Nvidia's software and hardware ecosystem. According to a September 30 Reuters report, the release includes open-source libraries for AI computation and chip-to-chip communication, as well as Ascend support for the high-level programming language TileLang.

DeepSeek says the tools — for which Huawei provided full support during development — are intended to simplify programming while enabling developers to fully leverage the hardware's performance. The two companies also worked together to optimize computation and communication on a supernode system built around 128 Ascend 950 chips. The work addresses two requirements for running large AI workloads across multiple accelerators: performing calculations efficiently on each chip and moving data quickly enough between them to keep the processors occupied.

The released libraries include DeepGEMM-Ascend, which handles matrix multiplication and other calculations used in DeepSeek's models. …