Deepseek just open-sourced the whole software stack for running its models on huawei chips
deepseek just open-sourced the whole software stack for running its models on huawei chips: the tilelang compiler, compute libraries, and distributed communication layer, mirroring its nvidia stack one for one. china’s compute counter-move is being shipped as open source, not as chips.
the bottleneck for domestic ai is now a software question, and it’s being answered in public.
Context
Verified date: DeepSeek announced on Sep 30, 2026 via its WeChat account that it open-sourced infrastructure components for Huawei's Ascend platform. Reuters says the move is part of a partnership with Huawei to develop programming tools for Ascend chips. The Tencent News report lists a TileLang compiler tool, DeepGEMM, DeepEP, TileKernels, FlashMLA and DeepSelect, which it says correspond one to one with components DeepSeek released earlier for Nvidia platforms.
Chip Dispatch reports Ascend versions of TileLang, DeepGEMM, DeepEP, TileKernels, FlashMLA and DeepSelect, each with a direct Nvidia counterpart.
The date, the compiler, compute library and communication layer, and the one-for-one mirror with the Nvidia stack match the reports. The Chinese-language report supplies the component list; the repository for the Ascend TileLang variant is tilelang-ascend. The post's 'whole software stack' goes beyond the six components named. 'The bottleneck is now a software question' is the author's opinion.
Related work
- tile-ai/tilelang-ascend ↗Ascend TileLang adapter.
- Reuters report ↗Sep 30, 2026.
- Chip Dispatch ↗Component list.
Watch next
- Read the tilelang-ascend README for which Ascend chips the compiler targets.
Sources
- DeepSeek partners with Huawei to develop chip programming tools, Reutersreuters.com
- DeepSeek Open-Sources Ascend Software Stack, Chip Dispatchchipdispatch.com
- DeepSeek开源昇腾基础组件, 腾讯新闻news.qq.com
Provenance
The note above is reproduced unedited from the original post, first published on Threads on 1 October 2026 at 09:15 IST. Sources are the papers and datasets the note draws on.
View the original post ↗Embed this note
More notes
The air is now being asked to keep its own ledger
the air is now being asked to keep its own ledger: ecmwf’s aifs compo becomes the first ai model to forecast atmospheric composition globally every three hours, cleanair simulates 365 days of pm2.5 over china in ten seconds, and a unified framework maps six pollutants at one kilometer across the whole country. the air now files its own composition report.
read the note →The current is now being asked to draw its own map
the current is now being asked to draw its own map: china’s langya 2.0 predicts six ocean phenomena including internal waves and mesoscale eddies, a deep net called wenhai resolves eddies globally with air sea flux formulas built in, and scripps infers surface currents from the way temperature patterns deform in satellite images. the ocean now files its own circulation report.
read the note →The soil is now being asked to report its own carbon
the soil is now being asked to report its own carbon: a nix color sensor paired with generative data augmentation predicts soil organic carbon without a lab, random forest drives 74 percent of soil health mapping studies, and sentinel 2 tracks five year carbon change across france and italy from 922 samples. the dirt now files its own carbon account.
read the note →