Oh my tmux! My self-contained, pretty & versatile tmux configuration made with 💛🩷💙🖤❤️🤍

LLM notes, including model inference, transformer model structure, and llm framework code analysis notes.

learn gpu cuda programming by examples

CUDA 算子手撕与面试指南

Material for gpu-mode lectures

📚200+ Tensor/CUDA Cores Kernels, ⚡️flash-attn-mma, ⚡️hgemm with WMMA, MMA and CuTe (98%~100% TFLOPS of cuBLAS/FA2 🎉🎉).

FlashMLA: Efficient MLA decoding kernels

DeepEP: an efficient expert-parallel communication library

Examples for using ONNX Runtime for machine learning inferencing.

ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator

Use your Neovim like using Cursor AI IDE!