Louis Aeilot’s Blog
-
1
北海之北
-
2
質疑莊子
-
3
When the Answer Arrives Late: Early-Exit Decoding in Modern LLMs
-
4
How Close Is FlashAttention to the Limit? Understanding Attention Through Data Movement
-
5
Beyond FLOPs: How COSMA Builds Parallel Matrix Multiplication from Communication Bounds
-
6
The Red-Blue Pebble Game: Why Faster Processors Still Have to Move Data
-
7
Git Needs a Trash Can
-
8
CS336 Assignment 1: Large Language Model Training and Inference
-
9
RoPE: Properties, Patterns, and Long-Context Behavior
-
10
sudo shutdown -r now