DeepSeek's near-hardware-limit kernels hint at a new model, possibly Ascend-trained
teortaxesTex · x · 2026-09-30
X user teortaxesTex argues DeepSeek would not have achieved 99.8% of the hardware limit on GEMM and 98% on MegaMoE and open-sourced those kernels without training something usable end to end — the kernel release likely supports post-training for an upcoming model. He speculates the rumored small single-GPU model may be Ascend-born. Unverified speculation.
Related event: Rumors say DeepSeek now trains on Huawei Ascend 950; V5 claims unverified(5 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