Developer Velocity You Can’t Unsee: Introducing GroqFlow™

Introducing GroqFlow for Developer Velocity

The industry needs an automatic, optimizing compiler that targets artificial intelligence (AI)-specific hardware. Today there are many solution stacks that only offer one or two of these three properties–automatic, optimized results, on the right hardware target. At Groq, we obsess over developer velocity: the idea that you should get from where you are to your […]

Jonathan Ross: ‘Every. Word. Matters.’

Nikki Ritcher Photography, Nikki Ritcher

This interview was originally published in EE|Times Weekend. Reposted with permission. Jonathan Ross is Groq’s founder and CEO. Prior to founding Groq, he began what became Google’s TPU effort as a 20% project, where he designed and implemented the core elements of the original chip. Jonathan next joined Google X’s Rapid Eval Team, the initial stage […]

Year of the Compiler

Blog Header Feb 22 22 copy

I’ve had an eye-opening month and I have three stories to share. Groq recently kicked off the release of our “early adopter” SDK, marking Groq Compiler as the primary means of programming GroqChip™ accelerators. Now, I’ve built my career on kernel optimization – meticulously coding important workloads specifically for targeted hardware. Sometimes Verilog has felt […]

AI Accelerator Start-up Meets Coaching Company?

GroqBoon 900

Lessons from a Progressive Partnership Between Groq and Boon “If leaders hope to grow their companies past the start-up phase, it’s essential to scale with a balanced leadership approach – one that pulls the best from good people instead of unintentionally pushing them out the door. When these leaders partner with experienced coaches, who understand […]

Talent, Locations, and Being Different. Groq’s Growth Success

Groq Growth

Groq grew significantly over the past year, from a small but driven team of 50 people to being more than three times that size. This would be a significant challenge for any start-up, under any circumstances. But 3x growth during a global pandemic forced us to examine how teams of highly talented people can be […]

Hold my FPGA: GroqChip™ takes the Cake for LSTM


This year I made the leap to join Groq after a decade of creating high performance applications for FPGAs (Field Programmable Gate Arrays). I was immediately curious to see how the GroqChip™ accelerator and its Tensor Streaming Processor (TSP) architecture measured up to FPGAs in terms of flexibility, performance,and programmability. This blog post summarizes my […]

Developer Velocity


Often when I talk with architects on the cutting edge of machine learning deployment models, there is a consistent theme to the conversations: developer velocity is slowed down by the tools we use. This is a challenge that needs to be overcome. We have the world’s smartest innovators, but they can’t try their new ideas […]

Brave Thinking

Groq Blog FullCircle 1

I started out in the 1990s as a patent attorney, and over the years I’ve worked with some very, very bright inventors. I love doing IP work with cutting-edge technologists — you walk in the room, check your ego at the door, and learn from experts in their fields sharing visionary ideas.  After six years […]

Groq Gives Hope

Groq Cares copy

What else does the team at Groq do besides simplify compute for the world? They give back; as they should. In celebration of Companies that Care Day, I wanted to shine the spotlight about how the Groq team decided to become Champions for Children this past Holiday Season.  Due to COVID-19 infection control, Lucile Packard […]

Honoring Women of the Past, Hearing Women of the Present

Women of Groq

Each year, the month of March is dedicated to honoring the countless contributions that women have made to history and to contemporary society. As I reflect on the trailblazers that led the way for change, I think about the women I’m surrounded by here at Groq. These are the next generation trailblazers.  At Groq, we […]

Hello Canada! New AI Opportunities in Toronto

daniel novykov Toronto driving Square

We just keep growing. As Groq continues its amazing trajectory, we’re excited to expand our footprint in Toronto, Canada. My roots are in Canada, where I attended the University of Waterloo in Ontario, studying Electrical Engineering. Toronto has become a hotbed for innovation in the fields of artificial intelligence and machine learning.  Toronto is also […]

Come Join Our Elite Team of AI Innovators

Engineer Talent

Artificial Intelligence is exploding. And with it comes amazing new careers in computational engineering, semiconductor development, systems integration and data science. The technology seekers, thinkers and doers in these fields all have an insatiable curiosity for knowing the unknown and innovating in never-before-thought-of ways. They are literally reimagining compute. At Groq, this is what we […]

The Shortest Path to Performance

groqnode 1

With over 1,000 attendants and more than 100 speakers, the AI Summit is the industry event for the AI hardware ecosystem. The event offers unique perspectives from industry luminaries and market perspectives.  On September 29th, 2020, Jonathan Ross, Groq’s co-Founder and CEO delivered one of the keynotes at the event. He did this on the day […]

Groq Adds Responsiveness to Inference Performance to Lower TCO

groq whitepaperblog 1

Running a batch size of one, which refers to computations on a single image or sample during inference processing, is a valuable option for many machine learning workflows – particularly those that require real-time responsiveness. However, small batch sizes and batch size 1 introduce a number of performance and responsiveness complexities to machine learning applications, […]

Groq Tensor Streaming Processor Architecture is Radically Different


How is Groq’s Tensor Streaming Processor architecture different? Conventional processor architectures are complex configurations of complicated control circuitry, multifunctional cores, and multi-level caches. Groq’s TSP architecture’s unprecedented computing power and efficiency is driven by simplicity, enabling superior compute density, predictable performance, and easy deployment at scale! Reach out to us today to learn more about how […]

Groq’s Tensor Streaming Architecture

groq tensorflow

Tensor-Streaming Architecture Delivers Unmatched Performance for Compute-Intensive Workloads Businesses and governmental entities are increasingly turning to compute-intensive applications, such as machine learning and artificial intelligence (AI), to enhance customer experience, increase competitive advantage, and improve security and safety in communities. However, achieving and maintaining the high-performance processing that these workloads require is extremely difficult due […]

Why AI Requires a New Chip Architecture

groq architecture chip

Artificial intelligence (AI) is one of the most hyped buzzwords in technology today. But while everyone may be talking about AI, a much smaller number of people are successfully doing AI.  According to a McKinsey report cited by Forbes, nearly three-quarters of over 2,000 organizations surveyed expect to increase investments in AI in the future, […]

World, Meet Groq

Sketch Chip Processor black

Businesses and governmental entities are increasingly turning to compute-intensive applications, such as machine learning and artificial intelligence (AI), to enhance the experiences of customers, increase competitive advantage, and improve security and safety in communities. However, achieving and maintaining the high-performance processing that these workloads require is extremely difficult, largely due to the growing complexity of […]