Dao-AILab

mentions 3 type Organization feed RSS

// recent coverage 3 mentions

17:59

2026-09-07

research.colfax-intl.com

machine-learning

Optimization diaries: S/P ping-pong for FlashAttention-4 decode

A new optimization for FlashAttention-4 (FA4) decoding on NVIDIA Blackwell GPUs overlaps softmax and matrix multiplication operations by using spare tensor memory (TMEM) in a ping-pong scheme, achievi…

20:46

2026-07-12

nanduruganesh.github.io

artificial-intelligence

Flash-MSA: Accelerating Million-Token Training with Sparse Attention Kernels

A developer released the first open-source training kernels for MiniMax Sparse Attention (MSA) on Hopper and Blackwell GPUs, enabling efficient million-token training with sparse attention. The kernel…

07:54

2026-07-09

github.com

artificial-intelligence

LingBot-World 2.0: Interactive world generation from image, text, and actions

LingBot-World 2.0 (LingBot-World-Infinity) introduces unbounded interaction horizons, rapid 60fps 720p video generation, diverse interactive elements, and an agentic harness for world modeling. The re…

// co-occurs with top 8 entities

MiniMax 1 Spheron 1 DeepSeek 1 GLM 1 LongCat 1 NVIDIA H100 1 NVIDIA B200 1 NVIDIA 1

// topics top 6 topics

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