Design Conductor 2.0: An agent builds a TurboQuant inference accelerator in 80 hours

TL;DR

Design Conductor 2.0 autonomously creates complex hardware accelerators, exemplified by an 80-hour TurboQuant inference accelerator, leveraging advanced multi-agent systems and frontier models.

Contribution

An updated multi-agent system capable of autonomously designing high-quality hardware accelerators for large models, handling larger tasks than previous versions.

Findings

Successfully designed an FPGA-based TurboQuant inference accelerator with 5129 FP units.

System handled 80x larger tasks with higher quality compared to prior work.

Analyzed empirical characteristics and limitations of the design process.

Abstract

Driven by a rapid co-evolution of both harness and underlying models, LLM agents are improving at a dizzying pace. In our prior work (performed in Dec. 2025), we introduced "Design Conductor" (or just "Conductor"), a system capable of building a 5-stage Linux-capable RISC-V CPU in 12 hours. In this work, we introduce an updated multi-agent harness powered by frontier models released in April 2026, which is able to handle 80x larger tasks, at higher quality, fully autonomously. Following a brief introduction, we examine 4 designs that the system produced autonomously, including "VerTQ", an LLM inference accelerator which hard-wires support for TurboQuant in a 240-cycle pipeline, starting from the TurboQuant arXiv paper. VerTQ includes heavy compute processing, with 5129 FP16/32 units; the design was mapped to an FPGA at 125 MHz and consumes 5.7 mm^2 in TSMC 16FF (8 attention pipes). We review the key new characteristics that enabled these results. Finally, we analyze Design Conductor's token usage and other empirical characteristics, including its limitations.