Joa Ebert

• SVP Technology & Architecture @ltnglobal • Previously @maketv, @defrac_ and @audiotool • Probably not the @joa you mentioned in your tweet

[Joa Ebert @joa]

Rocket jump 😍

[Tesla @Tesla]

Do a kickflip!

[Joa Ebert @joa]

And by the way 🎤🫳 : https://t.co/ItA2aITrDR

Phobos has now a home that's a bit more polished than a bare github repo :)

[Joa Ebert @joa]

👀
Integrating @OpenBMB 's latest drop into phobos-lang; I'm also pretty sure the elastic cache would be very efficient on small devices.

[Joa Ebert @joa]

@golang Hey folks, are you aware https://t.co/lvEfCGrr99 is having trouble? This will hang forever: wget https://t.co/ylPvTovyH7

[Joa Ebert @joa]

It also included a bit of uncanny existential crisis: "are we machines, or are we dreaming?". You can listen to machine_heart.js, a purely functional song, at https://t.co/xlwK11gfbm

[Joa Ebert @joa]

Æon learned to talk. My purely functional audio engine now has a formant speech synth and a vocoder. No samples. Just a (very basic) model of a throat as a function of t.

[Joa Ebert @joa]

Then I asked Opus 5.5 for a track. It wrote the lyrics as phonemes on a beat grid:

S IH S | T AH M | AA N | L AA IY N

That's "system online".

[Joa Ebert @joa]

Is it better than llama.cpp? Absolutely not. llama.cpp runs everywhere, and I optimized for one card hardly anyone cares about. But for that card I can tell you exactly where the time goes.

Blog Post: https://t.co/Loe7PMVCcV

v0.1.1, Windows and Linux: https://t.co/mxXidHTMDd

[Joa Ebert @joa]

My GPU is from 2019 and has 8 GB of VRAM. It now runs a 35B MoE that doesn't fit on it at 55 tok/s.

Every kernel is compiled at runtime from Phobos, a toy kernel language I wrote to learn what a kernel even is. No cuBLAS, no CUDA toolkit. Just the driver.

[Joa Ebert @joa]

No knobs. Phobos sizes its expert cache by free VRAM and the CPU computes the misses. When the desktop grabs 2 GiB mid-session, it keeps ~75% of its decode speed. llama.cpp at its fastest setting keeps 30% (-ncmoe 36 survives it, but runs slower all the time).

[Joa Ebert @joa]

This is @typesafeai #jev on the decks. I clearly need to tweak the context more. All parameters / decisions are driven by the model. It's similar to Jev playing Doom with a decision tree of what to do.

[Joa Ebert @joa]

Making launches where the compiler cache is cold more entertaining. #phobos #mlir #llvm

[Joa Ebert @joa]

@mitsuhiko The vast amount of generated output.

[Joa Ebert @joa]

I added @OmarchyLinux mode to Phobos. Because it's that's what you do in 2026 🤘(I had to use a tiny model, as otherwise the vid capture wouldn't work 😅)

[Joa Ebert @joa]

Use Jev to reduce the comment vomit in your code. 🤢 https://t.co/vSulK2Ldzw

[Joa Ebert @joa]

Can anyone recommend a cheap platform that allows me to rent a H100 where I can run ncu and nsys for perf tuning?

[Joa Ebert @joa]

New benchmark results. Ternary-Bonsai-2-27B-PTQ1_0 at the bottom. 46.12 tok/s vs 29.36 tok/s 🚀 #phobos #compiler #mlir #gpu #llm #inference

[Joa Ebert @joa]

Added reuse of Hadamard in Phobos and we gain another 24% during token generation; this puts Phobos at 1.47x of @PrismML s llama fork 🚀🚀🚀

#gpu #compiler #llm