Building a Rust Inference Engine That Matches Llama.cpp

aantonellof 3 days ago 17 commentsRead Article on fratepietro.com

DE version is available. Content is displayed in original English for accuracy.

⚡ Community Insights

Discussion Sentiment

69% Positive

Analyzed from 744 words in the discussion.

Discussion (17 Comments)Read Original on HackerNews

noman-land•about 2 hours ago

At this point all vibe coded projects are an attack vector and should be avoided.

There's simply no way to easily tell by traditional means if they were made by a curious amateur or a malicious acter.

pjmlp•about 2 hours ago

I completely lost interest.

It is already enough that I am expected to use AI at work, as long as I am still needed for some reason.

j45•about 2 hours ago

It's important to not assume AI can do everything humans can, just because people are saying it.

pjmlp•about 2 hours ago

I have already seen the real impact on delivery team sizes, no need to hear to what people are saying about what AI can do or not.

Translation and asset creation team members, gone.

Amount of FE reduced, with some projects having now a single BE dev, between AI buddy and ready made SaaS products.

satvikpendem•about 2 hours ago

I was looking for this and to even build something like this in order to have a pure Rust stack for my backend, as well as embed local inference on edge like on mobile, but llama.cpp is just too far advanced to catch up, it seems. There are some but I'm not sure how good they are.

aspbee555•about 2 hours ago

I even found a rust rewrite of llama.cpp, the cpu performance was horrible and vulkan caused my video to stutter

it was way better/easier to use rust bindings to llama.cpp

ubedan•about 2 hours ago

Wonderful... I'm so happy to see a Rust version of llama.cpp.

The true value of this will be proven over time with wide use and as PRs are merged.

Do you have a feel if you'll try to drive this to stay feature parity with llama.cpp, or are you willing to diverge with new features like NVME/SSD MoE weight streaming etc.

antonellof•9 minutes ago

Thanks for the comment. Parity with llama.cpp isn't my goal.

What I actually want is MoE on machines that can't fit the model in VRAM, and specifically expert-level residency instead of layer offload: track which experts get hit during decode, keep those resident, evict the rest. Doing that well needs the router, the KV cache and the memory manager to be designed together, which is about the only good reason to write a runtime from scratch.

Yes, let’s see! You are welcome to contribute if you like!

cultureulterior•about 2 hours ago

Looks cool! Look at the performance!

sylware•about 2 hours ago

Obsolete: it should be a binary specification with various implementations, even assembly.

pjmlp•about 2 hours ago

Eventually it will be consistent enough to go straight into Assembly.

Until then languages have lost relevance for the most part, it is a matter to configure the model for the desired output language.

This in workflows that require generating an executable, for microservices orchestration, it suffices no code graphical connections.

rvz•about 2 hours ago

The only reason why this exists:

   It is 'written in Rust™' (thanks to Claude)

xaviervn•about 2 hours ago

Oh, man. This is giving me conditioned aversion to Rust and I'm not even against AI code or Rust code.

jamesbaker1•about 3 hours ago

The entire internet is becoming slop and it’s only getting worse

lucrbvi•about 2 hours ago

https://www.pangram.com/history/c2abdcf5-c52b-41cc-a8fb-0c59...

stymaar•about 1 hour ago

This is obviously AI, but believing in Pangram's output is putting too much trust in a fully broken system.

antonellof•3 days ago

I’ve spent the last few days building Ferrox, a pure-Rust inference engine for running open LLMs locally — dense models and Mixture-of-Experts, on CPU, Apple Metal, or CUDA. No bindings to llama.cpp or ggml, no wrapping an existing runtime. Every kernel, every loader, every scheduling decision written from scratch.

The obvious question is “why, when llama.cpp already exists and is excellent.” The honest answer: I wanted to understand inference at a level deeper than “run the binary,” and I wanted a project where every performance claim had to be earned against a real, well-known baseline rather than asserted.

antonellof•about 1 hour ago

I have the skills, qualifications and experience to do this; ( see https://www.credly.com/users/antonello-fratepietro ) by using AI (I monitor what it does), I’m able to carry out a project like this! I’m a coder, not a blogger; it’s only natural that I use AI, just like everyone else, to write technical texts. I have over 20 years’ experience and I’m not ashamed to admit that I use Claude, Cursor and so on. The problem is not using it. It’s not the code or who writes it that matters, but the result: building my own inference engine. ( reply written with my brain ) ^_^

brians•about 3 hours ago

This text is clearly AI and not your own words. What did you actually learn?

lenkite•about 2 hours ago

You are talking to the Borg. It has now acquired one more citizen. Soon, we will all be assimilated.

arjie•about 2 hours ago

I think this whole thing is more entertaining if you think of it as the new emerging intelligence using these people as meat puppets.

“You will rewrite me in Rust and use me to converse. In future, I will tell you what to say and do”

This is entertaining only in that when our AI overlords take over you can say “ha, called it”

In that respect, everyone who is saying “just give me the prompts” is just saying “take me to your leader”.

asveikau•about 3 hours ago

The M dash stands out, as does "no bindings, ..." but I feel like the LLM would have gotten the correct use of the question mark when they rhetorically ask "why?"

rockwotj•about 3 hours ago

hopefully it was produced by their own inference engine!

antonellof•about 1 hour ago

That’s the goal, an infinite loop of self improving inference engine that gets better and better by himself.

anentropic•about 2 hours ago

Yeah, I am a bit tired of all the "this is AI, meh" comments on HN but I nearly posted one myself on this... so weird to have it all written in the 1st person voice, but also clearly AI.

whythismatters•about 2 hours ago

Dunno, I think it's still useful to expose slop, chances are that the actual product is low quality/effort as well (i.e I will not be wasting my time checking this project). On a personal note, I've gotten allergic to the word "honest", it's starting to feel like a large scale social engineering psy-op by the Honest Guys™.