Sign up free
Features
Resources
Pricing
Podcasts
Sign up free
Sign In
The GenAI Evolution Atlas
S1E5: How FlashAttention and MoE ...
AI
S1E5: How FlashAttention and MoE saved AI scaling
AI
The GenAI Evolution Atlas by Peter Liu
S1 · E5
Sep 1, 2026
40:45
RSS feed
Listen on
Share
About
Transcript
Episode notes
Efficiency & better building blocks
Make big Transformers faster, longer, and cheaper to run.
Keywords
Generative AI
LLM
Attention
KV cache
MoE
FlashAttention
Previous Episode
Next Episode