Tech Times

NVIDIA Diffusion LLM Hits 2.42x Throughput Without Retraining: Nemotron TwoTower Released

NVIDIA diffusion language model Nemotron TwoTower achieves 2.42x LLM inference throughput without a full retraining run, ...

Liquid AI's smallest model yet LFM2.5-230M beats models 4X its size at data extraction, can run 'anywhere'

LFM2.5-230M proves that while 3-billion-parameter models like VibeThinker are solving advanced calculus, a ...

The old model is broken. Telcos need to reinvent themselves

Consolidation may ease some pain for Singapore telcos, but it won’t address the many challenges the sector faces. Read more ...

Google's DiffusionGemma generates 256 tokens in parallel and self-corrects as it goes

Google's open-source diffusion language model generates 256 tokens in parallel and self-corrects, hitting 4x speed on one GPU at a cost to quality.
InfoQ

Meta Details GEM Ads Model Using LLM-Scale Training, Hybrid Parallelism, and Knowledge Transfer

Unlock the full InfoQ experience by logging in! Stay updated with your favorite authors and topics, engage with content, and download exclusive resources. Erik Steiger discusses the operational pain ...
blockchain

Ray's Disaggregated Hybrid Parallelism Boosts Multimodal AI Training by 30%

Ray's innovative disaggregated hybrid parallelism significantly enhances multimodal AI training efficiency, achieving up to 1.37x throughput improvement and overcoming memory challenges. In a ...
Forbes

Investors Back Parallel’s $20 Million Series B To Transform Special Education

Parallel Learning, a virtual special education platform, secured $20 million in Series B funding to address critical nationwide special education teacher shortages and resource gaps. The company ...
blockchain

NVIDIA NVL72: Revolutionizing MoE Model Scaling with Expert Parallelism

NVIDIA's NVL72 systems are transforming large-scale MoE model deployment by introducing Wide Expert Parallelism, optimizing performance and reducing costs. NVIDIA is advancing the deployment of ...