Viewing profile — olokobayusuf

There are over 2.5 billion Qualcomm processors in the world today (PC, mobile, automotive, etc). But the process for bringing AI models to run on Qcom processors is a (massive) pai…

Hey all! We're a small (semi-stealth) team that's been working on a tool to rewrite AI inference code from Python to C++ (similar to llama.cpp, whisper.cpp, and so on). Today, we'r…

Congrats on the launch!

We should collab! We prefer to be the underlying infrastructure behind the scenes, and have a pretty holistic approach towards hardware coverage and performance optimization. Read …

We're building something closer to this at Muna: https://docs.muna.ai . Check us out and let me know what you think!

This is super interesting! I'm the founder of Muna ( https://docs.muna.ai ) with much of the same underlying philosophy, but a different approach: We're building a general purpose …

Yup that's true. We do benefit from massive efficiencies though, thanks to LLM codegen.

Our primary use case is cross-platform AI inference (unsurprising), and for that use case we're already in production by startups to larger co's. It's kind of funny: our compiler c…

I'm founding a company that is building an AOT compiler for Python (Python -> C++ -> object code) and it works by propagating type information through a Python function. That type …

Function ( https://fxn.ai ) | Remote (US) We're building native code generation for AI developers. We generate high-performance C++/Rust to power open-source and on-device AI for o…

Link to original article that kickstarted all of this: https://medium.com/@eugeniyoz/powering-angular-with-rust-was...

A few weeks ago, Theo T3 posted a read-through of a Medium article showing how to augment an AngularJS website with WebAssembly in order to compute a factorial. I've been building …

When we trace Python code, devs have to explicitly opt-in dependency modules to tracing. Specifically, the `@compile` decorator has a `trace_modules` parameter which is a `list[typ…

Not entirely sure what you mean by having to deal with C-API and having a language spec. We're also not competing with LLMs at all--we use LLMs for said conversion (under strict ve…

Actually we're currently implementing Numpy (and PyTorch) support, and will cover a few other core scientific computing libraries like scipy. See docs: https://docs.fxn.ai/predicto…

Not quite. First, Function is designed to be truly cross-platform but libraries like Numpy aren't compiled for say WebAssembly. Second, the native libraries are usually built aroun…

Spot on! The majority of the innovation here is in building enough rails (specifically around lowering Python's language features to native code) so that LLM codegen can help you t…

I think a more pedantic way to describe what I mean is: "What if we could compile Python into raw native code *without having a Python interpreter*?" The key distinguishing feature…

Yes, we upload user code to a cloud sandbox in order to run our symbolic tracing and code generation algorithm. Beyond that, we also compile the generated native code in the cloud …

Way ahead of you: https://github.com/olokobayusuf/python-vs-rust/blob/main/Car... I've clarified that this is not designed to be a rigorous benchmark. We've got rigorous benchmarks…

More serious reply: us and Mojo have similar visions of where the world is going. The key difference between us is that Mojo is itself a new programming language. Sure, it supports…

We use LLVM! We're not translating Python directly to LLVM IR (I think I've seen other projects do this). We translate Python to C++/Rust first, where we have rigorous unit tests f…