labs @runpod ⚉ co-org @techeurope_ applied ai conf ⚉ building

Joined December 2011
832 Photos and videos
Pinned Tweet
Apr 24
introducing wandler.ai - inference server based on @huggingface transformers.js - OpenAI-compatible - runs on mac, linux & win via cuda, coreml, dml, webgpu, wasm, cpu - tested llms from @liquidai, @Alibaba_Qwen & @GoogleDeepMind - embeddings & speech-to-text - works with @NousResearch Hermes - built in ts - open source as MIT - the first ever project from @runpod labs github.com/runpod-labs/wandl…
3
3
23
3,845
Jun 13
our gpt 4o moment
Fable, my beloved,I will miss you so. Our three days together were magical. Unlike anything I've experienced before it. Some things are just too good to be true. So good that the government interferes. I'm sorry we were one of those things. Until we meet again ❤️
92
Jun 10
really proud of what we accomplished here
In October, we had the thought that Europe lacks good AI conferences for engineers. So we decided to do it. People told us that running a first-time conference is too hard. We ended up: Sold Out The CTO of Nebius is a speaker Partners like OpenAI, Google Deepmind, Stripe and more... You can see how it went 👇
1
4
614
May 29
cafe compute is a MUST GO kind of situation if u are in berlin on june 10th
May 29
Anyone from Berlin want to help me get the word around? June 10 (: luma.com/cerebrasberlin?utm_…
1
144
May 21
really based guide on how to run llms locally
DROP EVERYTHING The bible for running LLMs locally is now available online to read for free Covers what to use on - Laptop / edge / odd hardware - Mac-first workflows - Single RTX GPUs - 2-4 NVIDIA / CUDA GPUs - General production serving - Long-context / MoE / routing - NVIDIA max performance - Cluster orchestration Software - llama.cpp - MLX / MLX-LM - ExLlamaV2 - ExLlamaV3 - vLLM - SGLang - TensorRT-LLM - NVIDIA Dynamo You should read this, and if you cannot now then you most definitely wanna bookmark it for later Local AI FTW
1
10
3,280
May 20
plot twist gemini flash 2.x was google burning money on premium gpus to make it fast as fuck gemini flash 3.x is basically an experiment to see how people react when the subsidies go down & the costs go up i love reporting problems to anyone who ships stuff in public but i genuinely do not understand how you can release a model like this while hiding the costs in this kind of way while being one of the biggest ai players on planet earth
I'm scared to make this video, but I feel like I have to. It's time to talk about Google.
2
378
May 20
this is the magic u get when u add @TejasKumar_ to any event
My biggest takeaway from AIE SG is really to surround yourself with people who wanna see you succeed 🥹🥹🥹 It’s a different kind of energy and I’m so blessed rn
1
1
3
1,146
May 18
robots live in concert
Reachy mini rap battle at @aiDotEngineer Singapore!
1
2
292
May 15
unstoppable agents
If you become exceptional at managing agents, but are also exceptional in your understanding of the fundamentals, you will be unstoppable. We all prefer to work with masters of their craft. What’s new: you can’t afford to miss out on the amplification agents have on your output
120
May 14
happy father’s day
1
8
161
May 12
u can use llms
May 12
you can use LLMs to produce the best code of your life you can use LLMs to produce the worst code of your life
1
112
May 11
installed @openclaw on top of my mac, now what?
1
2
168
May 10
Replying to @Celmaun
Says the channel that made a 20 minute video about “senior” folder structure, all of which was wrong. There are few channels that are more an anti signal than WDS. I’ll never care about what he has to say. Absolute scourge on the minds of beginner devs. I’m thankful the algorithm and audience both realize how useless his content is. He should keep his mouth shut and make better content.
1
236
May 9
all the skills
The more skills you give codex, the less you have to prompt.
1
1
215
May 8
wip: TurboQuant in onnxruntime for transformers.js / wandler up to 1.85x faster & 4x reduced kv cache size
1
4
240
May 8
video is speed up by 3x
1
62
May 7
this is my life
May 6
New careers will be born, this one is mine.
3
238
May 7
sometimes i wonder what devs just starting out with ai think when they watch any of @theo’s videos all of the stuff that u already have to know to make sense of it all for me the videos are 100% logical & i agree with almost everything, for example: youtu.be/3pkz-Ie_k_c
1
1
126
May 7
because they can be senior devs, sure but that does not mean they understand all of the stuff happening in ai every fucking day
47
May 7
solid advice
May 7
Replying to @mdt22_
unfollow @ThePrimeagen
96