iiinova — where your digital self keeps evolving

Reposted by Ivar Flakstad

Michael (compiler-errors) Goulet @errs.io · 02/07/2025

Howdy all. I'm unfortunately not going to be with my employer for much longer due to team relocation. If anyone has any info on roles that would allow me to continue my Rust compiler work (in New York City), they'd be greatly appreciated.

19345

Reposted by Ivar Flakstad

kb @keighbee.bsky.social · 13/06/2025

I'm writing an article series about creating tensors from scratch in Rust. #tensors #machine-learning #ml #ai huggingface.co/blog/KeighBe...

huggingface.co

Building Tensors From Scratch in Rust: Part 1, Core Structure and Indexing

A Blog post by Kyle Birnbaum on Hugging Face

083

Reposted by Ivar Flakstad

Rust Language @rust-lang.org · 05/04/2025

🦀 Hello World! The Rust project now has an official presence on Bluesky! ✨ We'll be posting the same on our Mastodon and Bluesky accounts, so you won't miss anything on either platform.

311459285

Ivar Flakstad @ivarf.bsky.social · 09/03/2025

Want an in depth exploration of the different hardware architectures within AI? Of course you do :) Another great article by Chris Fleetwood: fleetwood.dev/posts/domain...

fleetwood.dev

011

Reposted by Ivar Flakstad

narsilou.bsky.social @narsilou.bsky.social · 10/12/2024

Performance leap: TGI v3 is out. Processes 3x more tokens, 13x faster than vLLM on long prompts. Zero config !

1196

Ivar Flakstad @ivarf.bsky.social · 08/12/2024

True, but at the same time my man JJB famously said «Ooh! Ooh! Mooie! Woohoo! Aah!» So yeah

110

Reposted by Ivar Flakstad

kb @keighbee.bsky.social · 05/12/2024

Preliminary data shows the Apple Neural Engine uses ~94% less energy than the CPU and ~75% less than the GPU 🤯 On the On-Device team at Hugging Face, we've been profiling energy usage for CoreML models. Here’s some data I collected:

Chart Title: Model Hardware vs Energy per GigaFLOP.
Vertical Axis: mJ/GFLOP(Log)
Horizontal Axis: Hardware Type(CPU, CPU + GPU, CPU + ANE)
CPU: min 6.9 1st quartile 11.7 median 13.4 3rd quartile 35.6 max 53.1
CPU + GPU: 4.6 4.6 4.7 6.2 9.6
CPU + ANE: 0.9 1.0 1.1 1.4 1.8

241

Ivar Flakstad @ivarf.bsky.social · 28/11/2024

I, for one, don’t immediately see anything wrong with what you’ve said here. There are perhaps some exaggerations here and there to drive home your points, but the best thread/rant on the subject (from the side of outraged bluesky users) that I’ve seen

010

Reposted by Ivar Flakstad

Thomas Wolf @thomwolf.bsky.social · 24/11/2024

It's Sunday morning so taking a minute for a nerdy thread (on math, tokenizers and LLMs) of the work of our intern Garreth By adding a few lines of code to the base Llama 3 tokenizer, he got a free boost in arithmetic performance 😮 [thread]

527134

Ivar Flakstad @ivarf.bsky.social · 21/11/2024

I guess you’ll have to engage fervently with that content to bring it back. Good luck 🫡

000

Ivar Flakstad @ivarf.bsky.social · 20/11/2024

I was just about to tag you hehe

010

Ivar Flakstad @ivarf.bsky.social · 20/11/2024

In Norway we let penguins lead 🫡 en.m.wikipedia.org/wiki/Nils_Olav

en.m.wikipedia.org

Nils Olav - Wikipedia

240

Ivar Flakstad @ivarf.bsky.social · 20/11/2024

If you want to dive into async allocators a bit more: open.spotify.com/episode/2YGI...

010

Ivar Flakstad @ivarf.bsky.social · 20/11/2024

Our hardware is usually async in many different ways, but our default programming approach usually isn’t. For example we approach allocating memory as a sync operation, but it usually isn’t. We could be doing stuff while allocating. Async allocators has a host of fun problems though :)

120

Reposted by Ivar Flakstad

Vicki @vickiboykis.com · 20/11/2024

when you try to convert your text into smaller pieces but all it gives you is Elvish, that’s a tolkienizer

341006103

Ivar Flakstad @ivarf.bsky.social · 18/11/2024

RoPE can be confusing, so here’s a great write up by my buddy Chris Fleetwood on the topic: fleetwood.dev/posts/you-co...

fleetwood.dev

030

Ivar Flakstad @ivarf.bsky.social · 17/11/2024

I think you’re applying your own (better) logic and improving on what he actually means. Your point has merit, his does not. Hold people accountable to their exact phrasing.

000

Ivar Flakstad @ivarf.bsky.social · 17/11/2024

He specifically said to stop worrying about climate goals and instead funnel money into AI, no? That’s what you should either agree with or not. Applying AI in various fields is something else. Sounds good.

000

Ivar Flakstad @ivarf.bsky.social · 17/11/2024

Generalisations outside what exists/can be inferred in the training set? That is unfortunately impossible simply by how training works. I think continuing to fund ML research is essential. But there are a limited amount of geniuses out there. Wild spending will not improve anything.

100

Ivar Flakstad @ivarf.bsky.social · 17/11/2024

Hah I thought you blocked me for agreeing with you because my comments disappeared. Phew. I guess they’re gone because the parent comments were removed.

000

Ivar Flakstad @ivarf.bsky.social · 17/11/2024

MLE here. I don’t want to put you down or anything, but I think you should look into the specifics a little closer. It is correct that it can only solve the types of problems it has seen. If the model is able to generalise beyond that then we’ve achieved AGE. Which we have not.

100

Ivar Flakstad @ivarf.bsky.social · 17/11/2024

I work with AI. Specifically the actual implementation of them. The way LLMs approach to a problem is the exact same approach as finishing a poem. In other words it does not have the concept of problem solving, it is simply finishing text to the best of its abilities.

200

Ivar Flakstad @ivarf.bsky.social · 17/11/2024

Why would I follow you if I didn’t want rants and tangents? Go ahead :)

000

Ivar Flakstad @ivarf.bsky.social · 17/11/2024

It is! When he first shared the findings some time back I spent some time thinking about how to extract something valuable from it but came up short. All I’m left with is that it’s fascinating. I feel like maybe it could tell us something about how to choose optimal precision, but 🤷

010