NJF Capital Nicole Junkermann Team
🇫🇷 FR 🇪🇸 ES 🇩🇪 DE 🇮🇹 IT
Venture Capital
 
 
 

Groq

Helping real-time AI applications come to life today

CALIFORNIA, USA

 
groq-microchip.jpg

More about Groq

Groq is on a mission to set the standard for GenAI inference speed, helping real-time AI applications come to life today. An LPU Inference Engine, with LPU standing for Language Processing Unitâ„¢, is a new type of end-to-end processing unit system that provides the fastest inference for computationally intensive applications with a sequential component to them, such as AI language applications (LLMs). The LPU is designed to overcome the two LLM bottlenecks: compute density and memory bandwidth. An LPU has greater compute capacity than a GPU and CPU in regards to LLMs. This reduces the amount of time per word calculated, allowing sequences of text to be generated much faster. Additionally, eliminating external memory bottlenecks enables the LPU Inference Engine to deliver orders of magnitude better performance on LLMs compared to GPUs.

Groq in the news

NJF Capital Blog
Groq Wants To Reimagine High Performance Computing
Groq Wants To Reimagine High Performance Computing

Forbes talks to Jonathan Ross, the CEO and founder of Groq

Groq Acquires Dataflow Systems Pioneer Maxeler Technologies
Groq Acquires Dataflow Systems Pioneer Maxeler Technologies

Advances converged HPC and ML solutions with Groq's proprietary compute architecture and Maxeler's rich systems portfolio

Groq Closes $300 Million Fundraising Round
Groq Closes $300 Million Fundraising Round

Groq closed $300 million in new Series C funding, co-led by Tiger Global Management and D1 Capital

Groq Appoints Andy Rappaport to Its Board of Directors
Groq Appoints Andy Rappaport to Its Board of Directors

Prior to joining the Groq board, Rappaport was most recently a partner at August Capital where he helped oversee its meteoric growth, establishing it as one of the largest VC firms in tech

Groq AI Chip Benchmarks Leading Performance on ResNet-50 Inference
Groq AI Chip Benchmarks Leading Performance on ResNet-50 Inference

Groq’s level of inference performance exceeds that of other commercially available neural network architectures

Groq Releases New Tensor Streaming Processor
Groq Releases New Tensor Streaming Processor

Groq announced that its new Tensor Streaming Processor (TSP) architecture is capable of 1 PetaOp/s performance on a single chip.

Groq Adds Compute Veteran Stuart Pann to its Board of Directors
Groq Adds Compute Veteran Stuart Pann to its Board of Directors

In addition to Pann, Groq is announcing the addition of multiple senior industry players to its leadership team

Nicole Junkermann on Groq
Former Google Chip Guru Takes Novel Approach to AI at Groq

Startup is working on radical processor for machine learning. Groq pursues data centre and self-driving car markets.

Secretive Semiconductor Startup Groq raises $52m from Social Capital
Secretive Semiconductor Startup Groq raises $52m from Social Capital

Secretive semiconductor start-up Groq raises $52m from Social Capital.

Groq, A Stealthy Startup Founded By Google’s TPU Team, Is Raising $60M
Groq, A Stealthy Startup Founded By Google’s TPU Team, Is Raising $60M

Groq, A Stealthy Startup Founded By Google’s TPU Team, Is Raising $60M