Vibecoding an inference chip

ankitvgupta 132 points 50 comments November 20, 2026
ankitg.me · View on Hacker News

Discussion Highlights (14 comments)

datadrivenangel

Does not say what type of model or size they were serving, but one of the traces mentions Maple, which is a 20b model. Still, getting ~70+ tok/s is quite good.

codekansas

This is cool Next step is tuning your post training pipeline to optimize your model for your chosen FPGA architecture...

chalkycrimp

Good chance I'm not the only one thinking this: share the code

cpldcpu

I did something like this with Opus 4.5: https://github.com/cpldcpu/smollm.c It seems implementing transformers is the new "hello world" of AI assisted coding.

saejox

i wonder if we can emulate an FPGA on a rtx 3090? then test it on an AWS EC2 F2 few hours a day.

Archit3ch

Now do silicon. ;)

spwa4

I must say I do see one application for this, that you can't really match reasonably otherwise: you can bake weights into an FPGA and then run them for 5W at a speed that will be competitive with a big Nvidia card. (unfortunately for a decent model it will also be price competitive with a big nvidia card)

lxe

Repetitive "make it faster" prompting is essentially what all these "RSI" claims are

hoppp

This is exciting, I have been wishing for good ternary models for a while as it seems more effective and combining it with FPGA I think this is a super promising path forward.

jluxenberg

A fun and interesting project, but to spend $10k+ in tokens on a curiosity seems excessive! Outside of my budget for sure.

itissid

Someone mentioned that FPGAs though amazing to create bespoke chips that are fast, run into a fab capacity issue. Someone explained briefly to me that even if you could make an fpga that could do inference better than current GPUs it was economically possible to make them at scale. I can't recall whether that was for technology related issues or just because fab capacity is completely filled up.

mococa

What lack of responsibility

seanjhkwon

It shows the importance of automated indicators when giving AI huge tasks. Maybe more important than the intelligence of the model.

reuben364

Over the week or so I have vibe coded a Lean-like language with - quantitative types - a Rust-ish DSL that lowers into the base language - a C, LLVM, WebAssembly backend and a Verilog backend for a subset of the language - A RISC-V implementation written in the Verilog subset that runs Doom on my Arty FPGA. - A category theory and real number library - A graph storage engine with queries written using profunctor optics - A datalog with an egglog in progress - A Joern-like code analysis engine for C and C# using tree-sitter to parse - A React style framework - Editor plugins for my language All at varying stages of completeness. What you can do now is wild. My fear is a sort of Gell-Mann Amnesia effect where my lack of expertise in the area is causing me to miss major problems with it. But at least some part of it has to be real. I plan to announce it in a more official capacity once I've allayed those concerns ( https://wiz.badlydrawnwizards.com for a sneak peak, but sorely need to update the website) My bottleneck currently is CI capacity. I've turned every spare computer in my household into a Slurm node so I can run more testing locally to avoid wasting precious CI capacity.

Semantic search powered by Rivestack pgvector
13,334 stories · 126,150 chunks indexed