NVIDIA HGX B200

mentions 3 type Person feed RSS

// recent coverage 3 mentions

01:03

2026-08-16

changyi.fun

machine-learning

Attention Through Arithmetic Intensity

A technical analysis by an unnamed author, inspired by a post from Su Jianlin, derives the arithmetic intensity (FLOPs per byte) of attention during single-token decode, finding MHA has an AI of exact…

23:30

2026-07-28

together.ai

artificial-intelligence

Cursor and Together AI deliver real-time, low-latency inference at scale

Cursor and Together AI have deployed real-time, low-latency inference for Cursor's AI-powered coding platform using NVIDIA Blackwell GB200 NVL72 and HGX B200 hardware, achieving predictable worst-case…

00:00

2026-05-11

together.ai

large-language-models

Serving DeepSeek-V4: why million-token context is an inference systems problem

DeepSeek-V4's million-token context capability stems from a hybrid attention architecture that compresses context before KV storage, reducing cache pressure. Together's early bring-up on NVIDIA HGX B2…

// co-occurs with top 8 entities

DeepSeek-V4 1 Together 1 Compressed Sparse Attention 1 Heavily Compressed Attention 1 Sliding Window Attention 1 Manifold-Constrained Hyper-Connections 1 Muon 1 Cursor 1

// topics top 6 topics

artificial intelligence 3 ai infrastructure 2 ai research 2 machine learning 2 large language models 1 ai tools 1