cd/entity/neuronx-distributed· home› entities› neuronx-distributed
grep -l @neuronx-distributed /news/*.json | wc -l → 1

neuronx-distributed

mentions 1 type Organization feed RSS

// recent coverage 1 mentions

13:36
2026-07-13
dev.to
artificial-intelligence

Porting Gemma-4 (2B / 4B / 12B) to AWS Inferentia2

A developer ported Google's Gemma-4 family (2B, 4B, 12B) to AWS Inferentia2, overcoming three architectural obstacles that break the vendor stack. The port achieved 44 tok/s for the 2B model, 33-39 to…

// co-occurs with top 6 entities
Google 1 Gemma-4 1 AWS Inferentia2 1 Hugging Face 1 Neuron SDK 1 optimum-neuron 1