DeepSeek releases six GPU software modules supporting Huawei Ascend accelerators
Quick Look
Hangzhou-based DeepSeek released six software modules mirroring its prior open-source tools for Nvidia's AI chips, including an Ascend-compatible version of TileLang that now supports Huawei's Ascend 950 accelerators with native code generation and automatic scheduling, aiming to build an independent and controllable GPU software ecosystem.
AI-generated summary
Why It Matters
DeepSeek previously released open-source tools for Nvidia's AI chips and is now expanding compatibility to Huawei's Ascend accelerators to build an independent GPU software ecosystem.
Hangzhou-based DeepSeek released six software modules that mirror its prior open-source tools for Nvidia’s AI chips, aiming to build a new “independent and controllable” software ecosystem for graphics processing units (GPUs), according to a post on its official WeChat account.
Among the releases is an Ascend-compatible version of TileLang, a custom programming language designed to streamline the development of high-performance kernels – essential computation programs – to run on GPUs and central processing units.
While TileLang lists Nvidia as its primary back end, it now officially supports Huawei’s Ascend 950 accelerators, offering “native code generation, automatic scheduling, and synchronisation”, according to an update on the project’s GitHub page.
Open Questions
- What are the specific six software modules released?
- When will the Ascend-compatible TileLang be available for download?
- What performance benchmarks exist for the new modules?
- How does DeepSeek plan to monetize or distribute this software ecosystem?







