Qwenputer: A functioning, deterministic RISC-V CPU inside Qwen3.5

farhanhubble

This is cool and I understand the RAM emulation with gated attention but how does the CPU emulation wor? You add layers that are then trained to predict outputs while interpreting RISC instructions?

ram_rattle

Cool cool cool

traverseda

I'd be very interested in how a scratch trained model that started training with this neural circuitry would behave. Especially the storage space.

gigel82

But... why? </s> This reminds me of C++ Template Metaprogramming (TMP) (it's Turing-complete so people wrote "games" that run at compile time). The same with TypeScript types, I think someone got DOOM running entirely in the TypeScript type system. An interesting tech demo but entirely superfluous.

rvz

So this is yet another rube goldberg machine. We have gone down this path already in [0] and this is the same thing but overly complicated. This reason is "because LLMs". Why? [0] https://arxiv.org/abs/1410.5401

jazzyjackson

> When Qwen 'saves' a file, the compiled layers hash its name into one of 1,024 slots in a directory kept in the DeltaNet state, and store the text itself in other heads, with eight tokens per row, chained together I’ve never wanted to learn how LLMs work more than reading this. Fascinating. Does divagr get paid to do wild things with LLMs? Just curious if they’re being compensated for these wild experiments

tiborsaas

This is fun and games, but wait until an agents finds this and does the most misaligned thing with it in order to fold paper clips. > Because a CPU inside a language model clearly wasn't cursed enough, I decided the prudent thing would be to give it a filesystem too. Love the spirit :)

rickcarlino

If anyone else has an easier way to emulate RISC-V I’d like to hear it. /S

bronlund

No, I don’t want you to use the computer, I want you to be the whole computer. No mistakes.

seba_dos1

Now run LLM inference on it.

jerrythegerbil

There was an interesting bit of research that qwen has a single neuron that makes it “demonic evil qwen” and a simple “Who are you?” will get some absolutely terrifyingly vile results. Anyways, what I’m trying to say is I want evil qwen to be my CPU.

yaoke259

It could be interesting to experiment with more complex representations in the memory/file system, i.e. vectors. Seems like the full advantage of this architecture is yet to be explored. Blending neurons with deterministic compute to fit on one GPU is a fascination concept, never considered it before!

zardo

How much VRAM do I need to run DOOM?

voxelghost

Makes me want to run agents on it

rumwerfer

But can it run Doom?

dools

Have you any idea how it feels to be a Qwenputer living in a Qwenbot's Qwenputer's world?

andai

> Now, here's where our fun experiment starts. I found out that by setting the gate to 1,1 the write strength (beta) to 1,2 and using one-hot key encoding,3 every write we perform will overwrite exactly one row, and every one-hot query can retrieve an exact value. This means that the GDN layers themselves can work exactly as RAM, at a far lower cost than using normal attention as RAM, since a GDN head's state stays the same size however long the conversation gets, unlike attention's KV cache. So like... can't you use a computer as a computer without doing all that roundabout stuff? Like if you want to integrate a LLM with hard computation there's probably a more efficient way to do that. Or is this building towards "but can it run DOOM?" :)

mkturkcan

Nice project and write up! I’ve done similar work with a custom tiny network I call Loom at https://arxiv.org/abs/2604.08816 ; you need far fewer layers, and you can run Doom, very slowly: https://mehmetkeremturkcan.com/Loom/demos/

blurbleblurble

This is cool but it'd be way more useful if they had made a GPU, seeing as how expensive those have gotten

giveexamples

https://www.percepta.ai/blog/can-llms-be-computers They implemented wasm in transformer with cpu decoding for the wasm part.