DeepSeek's releases reportedly come surprisingly close to a full Ascend stack for frontier training
teortaxesTex · x · 2026-09-30
Citing an Astra analysis, teortaxesTex argues that DeepSeek's release does not yet amount to a complete Ascend hardware/software stack capable of reproducing a frontier training run — but it is surprisingly close. The post frames this as a major step for China's domestic compute ecosystem; an attached reply adds mocking commentary aimed at Dario Amodei, but the substance is the Ascend stack assessment.
Related event: DeepSeek's New Model May Be Trained on Huawei Ascend Chips(3 posts)→
More from Infra
- 8% of Asia-to-US air freight is now data center parts — 30 full freighters a day — yacineMTB · 2026-09-30
- mradermacher quants get Gemma 26B to 75 tok/s on 2x RTX 4060 8GB — Spiritual_Impress_30 · 2026-09-30
- Hugging Face ships tokenizers v1, often tens of times faster than v0.23 — ariG23498 · 2026-09-30
- Altman says OpenAI's custom chip program comes online in H1 2027, betting on inference advantage — johncoogan · 2026-09-30
- Rumor: DeepSeek's rumored single-GPU model may have been trained on Ascend — teortaxesTex · 2026-09-30
- AAOI burnt capex on US vertical integration, CW laser yield still poor — jwt0625 · 2026-09-30