Posts

Jump window workflow with Alfred and Hammerspoon

alfred hammerspoon productivity macos automation tech

Elementwise Add Kernel in CUDA

cuda basics tech

flash-attention Usage: a Worknote for LLM inference

llm tech

Enable Jupyter in Doom Emacs

tech emacs

Asyncio By Example: Implementing the Producer-Consumer Pattern

python coroutine tech

Emacs Lisp Introduction for Python Programmers

emacs lisp tech python

Reduce kernel in CUDA

cuda basics tech

Count the parameters in LLaMA V1 model

LLM tech

Get GPU Properties

gpu basics tech

Notes on LLM technologies (keep updating)

LLM tech

Memory coalescing in CUDA (2) – Matrix Transpose

cuda basics tech

Memory coalescing in CUDA (1) – VecAdd

cuda basics tech

LLVM Utilities (keep updating)

llvm cpp tech

Apple TV 折腾记

life

Best Practices for Python Programming (Continuously Updated)

python tech

OpenAI/Triton MLIR 迁移工作简介

triton system tech

Emacs Essentials

emacs tech

About me

about-me