All Topics
All Topics
Technology
Technology
AI
AI
Business
Business
Entertainment
Entertainment
News
News
Programming
Programming
Science
Science
Design
Design
Environment
Environment
Finance
Finance
Crypto
Crypto
Politics
Politics
Sports
Sports
Education
Education
Gaming
Gaming
Art
Art
Music
Music
Health
Health
Security
Security
Books
Books
Food
Food
Travel
Travel
Personal
Personal
Bluesky
Twitter

Understanding Modern GPU Architecture for Machine Learning: H100 and B200 Technical Analysis

We love TPUs at Google, but GPUs are great too. This chapter takes a deep dive into the world of NVIDIA GPUs – how each chip works, how they’re networked together, and what that means for LLMs…

Read the full article
matt_d11mo ago65 min readen

You might also wanna read

The Critical Role of GPU Kernel Quality in Machine Learning System Performance

Machine learning systems sit at the heart of modern AI workloads. In these systems, performance often comes down to the quality of a small n

mlc.ai·23d ago

The Critical Role of GPU Kernel Quality in Machine Learning System Performance

Machine learning systems sit at the heart of modern AI workloads. In these systems, performance often comes down to the quality of a small n

mlc.ai·23d ago

HIVE Digital's Paraguay-based A40 GPUs match Nvidia H100 performance in AI training benchmark

HIVE and Columbia University found Paraguay-based Nvidia A40 GPUs matched H100 performance in AI research, supporting the company's AI expan

ccn.com·21d ago

AI-Driven Approach for Portable GPU Kernels in High-Performance Computing

High-Performance Computing (HPC) applications increasingly depend on GPUs, yet developing optimized kernels across evolving GPU architecture

hgpu.org·1mo ago

Announcing GPU Droplets accelerated by NVIDIA HGX H100 in the EU

Demand for high-performance computing resources, particularly for cutting-edge training and inference workloads, continues to grow exponenti

DigitalOcean·9mo ago

Researchers Serve 229B-Parameter MoE Model Across Five Consumer GPUs Over Public Internet

We serve MiniMax-M2.5, a 229B-parameter mixture-of-experts model, split across five consumer RTX 5090s in five European countries. The stage

doi.org·13d ago

Nvidia GTC 2026: Rubin Chips Replace H200 & Cut HBM Costs

The artificial intelligence landscape is shifting beneath our feet. At the recent Nvidia GTC 2026 conference, the industry witnessed a parad

TECH CRATES·26d ago

Comments

Sign in to join the conversation.

No comments yet. Be the first.