Omar Kilani
@omarkilani
eng @groqinc, co-founder @rememberthemilk. @waymo fan account. you can just do things enthusiast.
We’ve deployed the tool call template update to @GroqInc. Looks good. Thanks @Kimi_Moonshot 🫡
We've just fixed 2 bugs in Kimi-K2-Instruct huggingface repo. Please update the following files to apply the fix: - tokenizer_config.json: update chat-template so that it works for multi-turn tool calls. - tokenization_kimi.py: update encode method to enable encoding special…
Getting emotional seeing this (haven’t slept in 72 hours, YOLO launched a 1T param model) Huge credit to the incredible teams at @GroqInc for the relentless grind that made this possible.
holy shit groq + k2 is fast af - video not sped up stuff is changing real fast
Did a thing 🤫
Aren’t they like unable to run models larger than 70B? And kimi is 1T
Ridiculously excited to welcome @glenmaddern to @GroqInc 🫡 We’re going to be doing some really cool things with MCP. Watch this space. 😎
So what's next? Well, as of last week, I am now the Head of MCP at @GroqInc! 🎉 You might not have heard of Groq—they make custom silicon for AI inference. Which makes running models on their cloud way faster than what you're probably used to. This clip is not sped up:
If this is you we’re hiring @GroqInc groq.com/careers/ Or DM me.
How to hire Engineers who Ship Kernels! vaibhawvipul.github.io/2025/04/22/How…
Groq 💗 OSS More to come. 🫡
Compound Beta is an awesome project led by @benklieger 🔥 To showcase the capabilities of Compound Beta I've kicked off another project called Groq Desktop Beta (fully open source!) which allows you to use local MCP servers with your favorite @GroqInc hosted models. A thread 🧵
.@benklieger has you covered for low latency agentic workloads via @GroqInc 's new compound AI system
Now in preview – Compound Beta, our first compound AI system on GroqCloud that can search the web and execute code 🔥 More in 🧵
.@GroqInc is building the world’s largest AI inference hyperscaler - and we need a leader to scale it. We’re hiring a Director of Engineering, Compute to take the platform powering real-time AI to the next level. Apply today. 🫡 grnh.se/dfdf14183us
The @GroqInc cloud, networking and inference teams just worked some black magic and improved TTFT ~5x in Europe and India. More to come. 🫡
Today, we release QwQ-32B, our new reasoning model with only 32 billion parameters that rivals cutting-edge reasoning model, e.g., DeepSeek-R1. Blog: qwenlm.github.io/blog/qwq-32b HF: huggingface.co/Qwen/QwQ-32B ModelScope: modelscope.cn/models/Qwen/Qw… Demo: huggingface.co/spaces/Qwen/Qw… Qwen Chat:…
Today, we release QwQ-32B, our new reasoning model with only 32 billion parameters that rivals cutting-edge reasoning model, e.g., DeepSeek-R1. Blog: qwenlm.github.io/blog/qwq-32b HF: huggingface.co/Qwen/QwQ-32B ModelScope: modelscope.cn/models/Qwen/Qw… Demo: huggingface.co/spaces/Qwen/Qw… Qwen Chat:…
Honored and proud to be part of @GroqInc reaching 1 million developers—a milestone reflecting the brilliance and dedication of an exceptional team. And we’re just getting started… 🤫
Thank you, all one million of you, keep building fast! 👏🚀📈
Okay ✅
imagine coding with @Alibaba_Qwen's Qwen2.5-Coder-32B-Instruct at @GroqInc speed... should we make it happen, chat?
When they write the book about Groq it’ll be legendary.
Going to deploy a lot more inferencing capacity for the word!
Doing Things ™️
Live from the event, $1.5B to have Groq further expand Saudi Arabia's AI Inference Infrastructure after a successful completion of our first datacenter project in the Kingdom.
.@GroqInc is a ridiculously fun place to work and we’re on the lookout for amazingly talented people to join us on the journey. If that sounds like you, you should definitely apply today: groq.com/careers/?gh_ji… (This position is on my team. We make tokens go brrrr and do…
The vibes are good on this YOLO launch. 🫡
Deepseek 70B Distill + Groq LPU Sleep can wait. Build fast! 🚀💪👀