Frontier Post Training Pipelines

Post-training analysis & summaries from frontier base model tech reports (continuously updated).

2026-10-08 · 3 min · 516 words · Xiyuan Yang

Advanced LLMs 1: Attentions

Frontier LLM's Attention (MQA, GQA, MLA, Linear Attention Family, Flash Attention Family, Sparse Attention Family, Advanced Attentions)

2026-09-30 · 9 min · 1733 words · Xiyuan Yang