APC, SD, and SF
Explanation of Automatic Prefix Caching (APC), Speculative Decoding (SD), and Split Fuse (SF).
Python
Create A LibTorch Project
How to create a LibTorch project.
VSCode: Debug Python
This post shows how to configure launch.json in VSCode for debugging Python.
Dive into Paged Attention
Dive into the paged attention mechanism of vLLM.
A Simple Pytorch Trainpipeline
How to build a simple Pytorch trainpipeline.