We just pushed another optimization to Mistral AI Mixtral 8x7 to Groq Inc. Users will see a ~20% throughput improvement 🙌. These enhancements are driven by compiler software team’s relentless focus on throughput and latency.

Open Source + Lightning Fast⚡ >>>

Come work at @Groqinc 👇🏽

We’re expanding the Groq Inc team. If you’re a no nonsense engineer able to do deep systems work with great intensity, DM me.

Come make Groq Inc even faster and better. We’re not stopping until we hit 0ms TTFT.

Researchers like Andrew Ng have praised Groq, one buzzy name, as the type of chip that works fast enough to take generative AI to the next level, especially as the field pushes toward agents.
hubs.la/Q02x8Jck0

How fun is this? Our new intern made a demo showcasing Gemma 7B vs ChatGPT 4 Turbo controlling two Ken characters in a retro game. You can see how many more moves Gemma produces in the text screen (red text). What a creative fun side-by-side. Groq vs Groq next?

Happy to see Groq continue to shine. Thanks for the analysis and recommendations!

The generation of actual jobs will come from more people working in the field of AI and pioneering developments in the field. In doing so and creating their own companies, more people will be hired in the field, resulting in more jobs created. hubs.la/Q02x8Jcg0

Congrats on the launch! We're thrilled that Vectorize is leveraging Groq Inc as their default LLM.

Mark your calendar for tomorrow at 11:30 PT. Our Chief Tech Evangelist, Mark Heaps, will be joining the fun

Thank you AI at Meta and Cerebral Valley for a great weekend of hacking. We loved seeing all of the applications the developers built powered on Groq!

See you tomorrow at the NYSE Tech Summit SF for an engaging fireside chat with our CEO & Founder, Jonathan Ross, together with Venture Capitalist, ACTAI Global, Bill Tai. hubs.la/Q02x7dYJ0

If orgs performances are attempting to catch up to Groq Inc benchmark numbers might I remind everyone that we're still running on our 1st gen LPU™, 14nm silicon. 2nd gen in progress is at 4nm which will leap Groq ahead again. I can't wait. Jonathan Ross has a plan.

Yeah open source is dead, let’s all pack it up 🤣🤣🤣

Lamma3 using Groq Inc and crewAI and this person built 5 SaaS ideas!
AI agents are an amazing unfair advantage if you do it right, we are seeing an array of useful use cases on the enterprise side as well.

mingxuanh.eth Groq Inc Awesome.

IMHO, competition is great, and it’s nice to see what the H200 can do at scale.

OpenAI should simply run GPT on the LPU. :)

(The exciting thing about this is that we’re still super early in the LPU performance story.)

Developers, are you seeing this? 👀

Our booth was hopping today at #ISC24 . Be sure to stop by tomorrow to experience the LPU™ Inference Engine by Groq - a hardware and software platform that delivers exceptional compute speed, quality, and energy efficiency.

Don't miss our Meet & Geek with our partners from Argonne National Lab in booth M19 at #ISC24 tomorrow! Meet the team and learn about our latest work together leveraging the Groq LPU™ Inference Engine and its related systems.