DeepSeek open-sources six tools to help Huawei Ascend chips replace Nvidia in AI
pstAsiatech · x · 2026-09-30
According to SCMP, DeepSeek has open-sourced a suite of six software modules tailored for Huawei's Ascend AI chips, mirroring its earlier open-source tools for Nvidia hardware, aiming to build an "independent and controllable" GPU software ecosystem amid US export curbs.
The highlight is an Ascend-compatible version of TileLang, a custom programming language for streamlining high-performance kernel development. While Nvidia remains its primary backend, TileLang now officially supports Huawei's Ascend 950 accelerators with native code generation, automatic scheduling, and synchronization. The release marks a significant step in China's push to build a self-sufficient AI chip software stack.
Related event: DeepSeek Open-Sources Full Ascend Toolchain, Taking Aim at CUDA(17 posts)→
More from Infra
- Mobile AI Factory: agents auto-build on-device SLMs with 19x less GPU time — pmttyji · 2026-11-16
- Stratechery's Fictional Obituary: Imagining Jensen Huang's 2026 Exit From Nvidia — Gregory_C_Allen · 2026-11-16
- vLLM serves DeepSeek V4.1-Flash at 954K tokens/s per GPU, $38.96/GPU-hour on GB300 NVL72 — bookwormengr · 2026-11-16
- Colossus 2's 1.2M B200s could generate ~$400B/year in tokens at DeepSeek Flash rates — bookwormengr · 2026-11-16
- BIS issues rule blocking remote access to US AI chips via third-country data centers — teortaxesTex · 2026-11-16
- Qdrant 1.20.1: 50% fewer cold-storage reads, ~2x faster quantization, agent-ready setup — qdrant_engine · 2026-11-16