Open-source openTPU shows AI designing its own inference hardware

The open-source openTPU accelerator, developed by AI agents, spans SystemVerilog hardware, an instruction set, a bit-exact simulator, a kernel language and compiler, and host software, running ten real-weight models on a Xilinx Kintex-7 FPGA card with bit-exact token output versus the simulator.

• Bilibili Releases Index-Translate Multilingual Model Family2026-10-05
• Developer Runs Qwen3.5 LLMs on Cheap FPGA Mining Hardware2026-10-04
• Study Reveals Authority Bias in LLMs2026-10-02
• Home-Trained 0.8B Decision Model Jeff Runs in ~30ms2026-09-28
• Transformers now runs llama.cpp quants2026-09-22