The GenAI Evolution Atlas
S1E5: How FlashAttention and MoE ...
IA
S1E5: How FlashAttention and MoE saved AI scaling
IA

The GenAI Evolution Atlas por Peter Liu

T1 · E5
1 sept 2026
40:45
Notas del episodio

Efficiency & better building blocks

Make big Transformers faster, longer, and cheaper to run.

Palabras clave
Generative AILLMAttentionKV cacheMoEFlashAttention