AMD releases dedicated ROCm 10.1 driver for Radeon RX 9000 and RX 7000 GPUs
Non-CUDA GPU backend item - cross-vendor awareness, not RTX 3090 CUDA serving.
Independent publication // local-first AI // field reports from owned systems
Nodehome
A running publication about local models, private inference, self-hosted agents, weird hardware, research sweeps, and the builders wiring their own AI stack together.
AI is getting physical again. It shows up in terminals, racks, side projects, and ugly little workflows people actually control.
Latest
Daily Sweep - Oct 05, 2026The program features a keynote and Q&A by Jürgen and short talks by Sakana AI researchers on our work at the RSI Lab. - Date: Monday, October 26, 2026, 15:00-18:00 JST - Venue: Hitotsubashi Hall, Tokyo - Language: English - Admission: Free (registration required) Register here: luma.com/kjf0z516 🐟
RAG or embedding pipeline development - potential local workflow pattern.
The Tao of Backup
ExplainDB: A Database System Built for Understandability
Welcome RL Environments to the hub
Hugging Face blog post - check for new model releases, library updates, or ecosystem shifts.
AMD B650 chipset lands on a $58 PCIe expansion card with four M.2 slots
Bus or storage bandwidth topic - relevant to the H12SSL-i's PCIe 4.0 layout.
Registration now open: From World Models to Real-World AI Luma: luma.com/kjf0z516 Join us on October 26 in Tokyo for a symposium with Jürgen Schmidhuber, who recently joined Sakana AI as Chief Scientific Advisor.
【受付開始】From World Models to Real-World AI - 日本から拓くAIの新時代 Chief Scientific Advisorとして当社に参画したJürgen Schmidhuber博士を迎えるシンポジウムを、10月26日（月）に東京・一橋講堂で開催します。 本日より一般申し込みを開始しました。Schmidhuber博士による基調講演とQ&A、 CEO David Haとの対談、Sakana AI研究者によるショート講演を予定しています。 お申し込みはこちら： luma.com/kjf0z516 🐟
Field Reports
builds, experiments, notesThree RTX 3090s, One 32B Model: A Pipeline-Parallel Canary
A current field note on why the 3x3090 serving path moved through pipeline parallelism, not tensor parallelism, for the tested 32B AWQ model.
Gemma 4 12B And The Sensory Agent Lane
A public-safe read on Gemma 4 12B as a local sensory preprocessor: useful for seeing, hearing, and structuring observations without turning into an action system.
Hardware
machines, thermals, economicsPower Caps On Three RTX 3090s: Bursts Versus Sustained Load
A measured note on 300W bursty inference, lower caps for sustained runs, and why power-cap sweet spots are workload-specific.
Parallel Agent Serving Is A Hardware Shape Now
A field-report read on 14x RTX 3090 agent serving, EXL3, FP8 KV cache, Aphrodite, and why concurrency is becoming the local hardware metric.