编码智能体构建FPGA LLM推理系统
在一份第一手记录中,项目作者称 Codex 与云端智能体使用 C++ 和 Verilog 配置了 AWS F2 FPGA 实例,使 LLM 得以运行。智能体完成了数百次实验,据称将首个位精确基线的速度提升 33 倍,并在 8,192 token 上下文下达到约 220–230 token/s。性能数据及编码智能体促成这项底层硬件工作的说法均来自单一来源,尚未独立验证。
这份详细记录显示编码智能体可能帮助工程师进入陌生的底层硬件领域,但其速度与能力声明尚未获得独立验证。
Or rather, I vibe-coded an FPGA into running an LLM. And it… just worked.
Friday. November 20, 2026
One of the more entertaining things about programming recently is that coding agents let me work in entirely new domains by giving me access to new programming languages and paradigms. Lately, that has meant hacking on hardware, now that writing low-level software is much easier. So, in this blog post, I’m going to try to recount the experience of vibe coding an FPGA, going through a series of “oh shit” moments several times, and giving myself a new appreciation for what’s possible if you have a large token budget (thanks YC) and interesting problems to point the models at.
I overheard some founders recently talk about how FPGAs work. I’ll admit I was relatively naive about them. I’d never really experimented with them in my startup or in college, so I knew little about them before. The basic idea I was familiar with: you can program a circuit into a reprogrammable chip. So rather than having a general purpose computing architecture (like a CPU) you can have a reprogrammable one, i.e. the configuration loaded onto the chip determines how its logic and routing are connected, and that (in theory) enables performance advantages. I also know that it took a mountain of C++ to write and involved manually analyzing waveforms for simulation and verification. I had never done this before though and it seemed cumbersome.