GoKawiilDeepSeek and Huawei release open-source tools for Ascend AI chips
DeepSeek, working with Huawei, has published open-source programming libraries for Huawei's Ascend AI chips, including DeepGEMM-Ascend for matrix computations and DeepEP-Ascend for chip-to-chip communication, plus Ascend support for the TileLang programming language. The tools were developed and tested on Ascend 950 hardware, including a 128-chip supernode system, according to a September 30 Reuters report.
GoKawiil's interpretation of the reporting above, not reported fact.
The release gives developers an alternative software stack for training and running large AI models without relying on Nvidia's CUDA ecosystem, which could lower a barrier to adopting Chinese-made chips. Because the libraries mirror DeepSeek's existing programming interfaces, they may ease the transition for developers already using Nvidia-based tools, potentially accelerating Ascend adoption amid US export restrictions on advanced chips to China.
- DeepSeek and Huawei jointly released open-source libraries for Ascend AI chips
- DeepGEMM-Ascend and DeepEP-Ascend handle computation and chip communication, tested on a 128-chip Ascend 950 supernode
- TileLang now supports Ascend, offering an alternative to Nvidia's CUDA programming model
Source: tomshardware.com — Etiido Uko, 2026-10-01
Published there as: “DeepSeek and Huawei release open-source Ascend AI programming tools to reduce reliance on Nvidia ecosystem”
Read the original report → The summary and analysis above are GoKawiil's own, written from reporting by the source above. Facts and quotes belong to the original publisher.