[CLSTR]
< Back to situations

Monitor this situation.

[SITUATION] · [QUIET] · [TECHNOLOGY]

3 clusters · 34 sources · 22 days · First seen · Last updated

NVIDIA Groq 3 LPX production and manufacturing

Overview

NVIDIA has entered full production of its Groq 3 LPX AI inference racks, following its December 2025 acquisition of Groq assets. The system is designed to complement NVIDIA’s Vera Rubin platform by specializing in the low-latency “decode” phase of AI model generation. Each rack integrates 256 Language Processing Units (LPUs) and utilizes 500 megabytes of on-chip SRAM to reduce memory bottlenecks.

Samsung Electronics is the exclusive manufacturer of the hardware, utilizing a 4-nanometer fabrication process. At the Hot Chips 2026 conference, it was noted that this mass production could return Samsung’s foundry unit to profitability as early as the third quarter, serving as a financial inflection point for its contract chipmaking business.

Nebius has been identified as the first AI cloud customer for the Groq 3 LPX system. To further expand its inference capabilities, NVIDIA has entered a multi-year collaboration with d-Matrix to integrate Raptor inference XPUs into NVIDIA MGX racks via NVLink Fusion. This partnership aims to provide a heterogeneous architecture that splits workloads between GPUs and XPUs, utilizing a 3D-DRAM architecture that offers a different technical approach to inference compared to the SRAM-based Groq 3 LPX.

Additionally, SpaceXAI has committed to deploying NVIDIA Vera CPUs as part of its next-generation AI architecture, with plans to extend capabilities to orbital data centers.

Entities

Groq · Nvidia · Vera Rubin · Nebius · Jensen Huang

Timeline

  1. 15 days ago

    [TECHNOLOGY] 3 sources
    NVIDIA expands AI inference capabilities with Groq 3 LPX and d-Matrix partnership

    NVIDIA is scaling production of the Groq 3 LPX inference accelerator and partnering with d-Matrix to integrate Raptor XPUs into MGX racks to optimize low-latency AI workloads.

  2. about 1 month ago

    [TECHNOLOGY] 4 sources
    Samsung foundry nears profitability via Nvidia Groq chip production

    Samsung's foundry unit may return to profitability this year as it begins mass production of Nvidia’s Groq 3 LPX AI inference accelerators using a 4-nanometer process.

  3. about 1 month ago

    [TECHNOLOGY] 28 sources
    NVIDIA enters full production of Groq 3 LPX AI inference racks

    NVIDIA has entered full production of its Groq 3 LPX inference accelerator, a system designed to boost low-latency AI agent performance. The hardware is being manufactured by Samsung and adopted by Nebius.

Sources

abmedia.io · beautytrends.pl · borncity.com · detlionblood32.wordpress.com · digitalphablet.com · europesays.com · finance.technews.tw · futurumresearch.com · gamemag.it · hwsw.hu · incomemagazine.ro · it-boltwise.de · ithome.com · jnilbo.com · koreaherald.com · losangelesweeklytimes.com · markets.businessinsider.com · marketwire.com · networkworld.com · newsable.asianetnews.com · newsbytesapp.com · nvidianews.nvidia.com · olhardigital.com.br · opensourceforu.com · pcgameshardware.de · sammobile.com · siliconangle.com · startupcafe.ro · technice.com.tw · tfmedia.co.kr · the-decoder.com · theascent.com · theregister.com · tomshw.it

This summary has been updated 1 time: see revision history