Iaroslav Elistratov

mentions 1 type Person feed RSS

// recent coverage 1 mentions

12:30

2026-09-02

iaroslavelistratov.github.io

artificial-intelligence

B200 Attention Kernel from Scratch to Near-SOTA in 60 Diagrams

A new technical blog post by Iaroslav Elistratov presents a visual guide to building a B200 attention kernel from scratch in CUDA and PTX, achieving 94.4% of FlashAttention-4 performance on 4K, 8K, an…

// co-occurs with top 5 entities

B200 1 CUDA 1 PTX 1 FlashAttention-4 1 Blackwell 1

// topics top 5 topics

artificial intelligence 1 machine learning 1 ai research 1 ai infrastructure 1 developer tools 1