Groq offers LPU
Groq LPU is a custom inference chip with on-chip SRAM and deterministic scheduling delivering low-latency AI inference for LLMs.
Groq LPU is a custom inference chip with on-chip SRAM and deterministic scheduling delivering low-latency AI inference for LLMs.
The Groq LPU (Language Processing Unit) is a tensor streaming processor that combines compute, SRAM, and networking on a single die. It uses a software-scheduled, deterministic execution model designed for predictable latency and high throughput on generative AI inference workloads.
In December 2025, Nvidia entered a non-exclusive licensing agreement for Groq's inference technology, validating the LPU architecture. Groq continues to operate independently and in June 2026 raised $650M to scale its inference cloud business.
| Attribute | LPU | Cerebras Cloud (Inference & Training Platform) | DataScale, RDU | DGX | |
|---|---|---|---|---|---|
| Provider |  |  |  |  NVIDIAnvidia.com$24.1B raised · Public | |
| Founded | 2016 | 2016 | 2017 | 1993 | |
| Sells To | Enterprise | — | Enterprise | Consumers, Enterprise | |
| Pricing Model | Recurring | — | Recurring, Software | Licensing, Product Sales, Subscription | |
| Ownership | Venture Capital | — | Equity, Venture Capital | Public |
Provider
Founded 2016
Sells To Enterprise
Pricing Model Recurring
Ownership Venture Capital
Provider
Founded 2016
Sells To —
Pricing Model —
Ownership —
Provider
Founded 2017
Sells To Enterprise
Pricing Model Recurring, Software
Ownership Equity, Venture Capital
Provider NVIDIAnvidia.com$24.1B raised · Public
Founded 1993
Sells To Consumers, Enterprise
Pricing Model Licensing, Product Sales, Subscription
Ownership Public
Hopper
nvidia.com
PowerEdge XE9680
dell.com
TPU
cloud.google.com
Trainium
aws.amazon.com
Wafer-Scale Engine
Instinct
amd.com
Tenstorrent Galaxy
tenstorrent.com
