Stories by buildbot

Why does it take so long to release black fan versions?

Nvidia Groq 3 LPX

Nvidia Nemotron 3 Super Delivers 5x Higher Throughput

Think Smart About Sparse Compute: LatentMoE for Higher Accuracy per Flop, Param

Nvidia Nemotron-3 White Paper [pdf]

Webb First to Show 4 Dust Shells 'Spiraling' Apep, Limits Long Orbit

Emerging Properties in Unified Multimodal Pretraining

Azure Maia for the era of AI: From silicon to software to systems

Making AI More Accurate: Microscaling on Nvidia Blackwell

Blackwell Tensor Cores support Microscaling formats for 4B inference

The Layoff

Pixel owners report problems after installing January 2024 Google Play update

Neural Network Quantization and Number Formats from First Principles

Introduction to MicroScaling (MX) for AI Tensors

OpenAI is paying out $51M to a chip startup that Sam Altman invested in

The first two custom silicon chips designed by Microsoft for its cloud

Ask HN: How can x/Twitter use groq for their AI legally?

"Serverless", GPU Accelerated OpenAI API Using Podman, Llama.cpp, and Systemd

Bandwhich: Terminal Bandwidth Utilization Tool