Deepseek releases open-source TileLang for Huawei Ascend chips
Deepseek and Huawei announced a collaboration to develop open-source software for Huawei’s Ascend AI chips, including TileLang, a programming language designed as an alternative to Nvidia’s CUDA. The release includes libraries for computation and data transfer between chips, all made available under an open-source license. Deepseek claims TileLang offers a simpler programming model than CUDA and…
Key points
- Deepseek and Huawei release open-source TileLang for Ascend chips, targeting Nvidia’s CUDA dominance
- TileLang includes computation libraries and data transfer tools, tested on Nvidia hardware before AGI use
- Huawei’s new AI processors face domestic demand shortages, reducing exports due to US restrictions
Research firm SemiAnalysis noted that CUDA’s moat is weakening, citing OpenAI’s Jalapeño chip outperforming Nvidia’s Blackwell in some scenarios. However, Nvidia still leads in agent workloads, and SemiAnalysis cautioned that its advantage lies in software integration rather than silicon alone. Earlier analysis highlighted Huawei’s CANN software stack as one of the few, alongside CUDA, to support DeepSeek V4 on day one.
China's AI industry closes ranks as Deepseek ships open-source software for Huawei's Ascend chips
The Decoder · 30 September 2026
Loading the full article…
This text was published by The Decoder and written by Maximilian Schreiner. It is reproduced here with attribution so you can read it in full; the rights remain with the publisher. Read it at the source ↗
Coverage and discussion
4sources- DeepSeek and Huawei release open-source Ascend AI programming tools to reduce reliance on Nvidia ecosystemPress · Tom's Hardware ·
- DeepSeek, Huawei Challenge the Software Powering Nvidia’s AI DominancePress · thedailyupside.com ·
- DeepSeek says it has partnered with Huawei to develop programming tools for Huawei's Ascend chips, including TileLang, an open-source CUDA alternativePress · reuters.com ·
The headline, key points and digest above were generated by Digest AI's editorial model from the linked sources. Automated summaries can contain errors: the sources are the record. Spotted a mistake? Tell us. Published by Martin K., who runs Digest AI and handles corrections.
More in Hardware & Compute
All →- Micron’s AI memory stock may jump 89% in 2027, analysts say · 3 src
- GitHub - W61k3r/LexiSuite-Releases: does qwen and gemma ok. · 2 src
- Nvidia shares fall 6% to 9% as AI selloff follows Democratic midterm sweep · 22 src
- Chinese AI lab Moonshot seeks Nvidia Blackwell access via European data centers, sources say · 6 src
- Asus zenbook a16 outperforms Nvidia RTX Spark for local AI · 1 src
Comments
via GitHub Discussions