Vibecoding an inference chip
ankitvgupta
132 points
50 comments
November 20, 2026
Related Discussions
Found 5 related stories in 140.1ms across 13,334 title embeddings via pgvector HNSW
- Vibecoding isn't as fun as writing code by hand meetpateltech · 16 pts · August 21, 2026 · 63% similar
- Vibecoding isn't as fun as writing code by hand Curiositry · 183 pts · October 06, 2026 · 63% similar
- I've vibe coded an application to see what it's like exitnode · 12 pts · August 10, 2026 · 60% similar
- AI Coding Without the Vibes riskone · 81 pts · August 16, 2026 · 60% similar
- Bend 2 and the Vibe-Coding Trap LiamPowell · 317 pts · September 18, 2026 · 58% similar
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.