# Cerebras: what I've logged

> Cerebras comes up in 2 posts of my AI log, from October 2026 to November 2026, and each item below links to the primary source. I filed it under agents and coding, science and frontier.

## Items

1. **Cerebras launches disaggregated inference** (Cerebras, 17 Nov 2026): Prefill runs on GPUs and decode on Cerebras CS-3, with a reported 5x throughput per megawatt on a GPT-OSS-120B endpoint versus a CS-3-only setup. [Primary source](https://www.cerebras.ai/blog/cerebras-launches-disaggregated-inference) · [Post](https://heyaliasif.com/ai/2026-11-18-cerebras-disaggregated-scribe-medical-slurm-hres#item-1)
2. **How we deploy trillion-parameter frontier models on Cerebras** (Cerebras, 24 Oct 2026): Worked example of serving Kimi K3 across 59 WSE-3T wafers with one layer group per wafer, claiming 1,000 to 2,000+ tokens per second. [Primary source](https://www.cerebras.ai/blog/how-we-deploy-trillion-parameter-frontier-models-on-cerebras) · [Post](https://heyaliasif.com/ai/2026-10-25-gvs5h-cerebras-trillion-memt#item-2)

## Posts

- 2026-11-18 [Cerebras disaggregated inference, Scribe v3 Live Medical, Slurm HRES](https://heyaliasif.com/ai/2026-11-18-cerebras-disaggregated-scribe-medical-slurm-hres)
- 2026-10-25 [GVS5H self-orchestration, Cerebras at trillion scale, MemT-1.0](https://heyaliasif.com/ai/2026-10-25-gvs5h-cerebras-trillion-memt)

Canonical: https://heyaliasif.com/ai/topics/cerebras