A pure-Python implementation of the Nvidia CuTe layout algebra intended to be approachable and easy to learn.

Low overhead tracing library and trace visualizer for pipelined CUDA kernels

NVIDIA Linux open GPU with P2P support

PyTorch Single Controller

eBPF-based GPU causal observability agent

AI agents running research on single-GPU nanochat training automatically

cuTile Rust provides a safe, tile-based kernel programming DSL for the Rust programming language. It features a safe host-side API for passing tensors to asynchronously executed kernel functions.

Automated CUDA kernel performance diagnostics from NVIDIA Nsight Compute (NCU) CSV exports.

通用高质量 Skills 合集🔥

Claw 们终将接管世界，PUAClaw is All You Need

A continuation of HomeBox the inventory and organization system built for the Home User

机场推荐与机场评测

BCC - Tools for BPF-based Linux IO analysis, networking, monitoring, and more

A Rust port of FlameGraph

Terminal UI for NVIDIA Nsight Systems profiles — timeline viewer, kernel navigator, NVTX hierarchy

A lightweight inference engine supporting speculative speculative decoding (SSD).

Muon is an optimizer for hidden layers in neural networks

Humanizer 的汉化版本，Claude Code Skills，旨在消除文本中 AI 生成的痕迹。

A curated list of awesome Claude Skills, resources, and tools for customizing Claude AI workflows

From Minimal GEMM to Everything

KsanaDiT: High-Performance DiT (Diffusion Transformer) Inference Framework for Video & Image Generation

Learn CUDA with PyTorch

Build compute kernels and load them from the Hub.

A sliding, tiling window manager for MacOS.

Github mirror of trition-lang/triton repo.

FP8 stochastic rounding

Quartet II Official Code