整理记录各个包管理器，系统镜像，以及常用软件的好用镜像，Thanks Mirror。 走过路过，如觉不错，麻烦点个赞👆🌟

A minimal GPU design in Verilog to learn how GPUs work from the ground up

Fully open reproduction of DeepSeek-R1

A high-throughput and memory-efficient inference and serving engine for LLMs

Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

Tensors and Dynamic neural networks in Python with strong GPU acceleration

manylinux docker images with CUDA Toolkit

best way to save what you love

Tile primitives for speedy kernels

经济学人(含音频)、纽约客、卫报、连线、大西洋月刊等英语杂志免费下载,支持epub、mobi、pdf格式, 每周更新

LLM101n: Let's build a Storyteller

A code generator from ONNX to PyTorch code

100 numpy exercises (with solutions)

Synchronize Vim, Tmux, and OS clipboards via OSC 52

CUDA on non-NVIDIA GPUs

Produce redistributable builds of Python

LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalability, and high-speed performance.

Collection of kernels written in Triton language

depyf is a tool to help you understand and adapt to PyTorch compiler torch.compile.

本项目旨在分享大模型相关技术原理以及实战经验（大模型工程化、大模型应用落地）

a huggingface mirror site.

AutoAWQ implements the AWQ algorithm for 4-bit quantization with a 2x speedup during inference. Documentation:

4 bits quantization of LLaMA using GPTQ

Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.

Awesome-LLM: a curated list of Large Language Model

Development repository for the Triton language and compiler

Numbers every LLM developer should know

Shell script for building your own static tmux release. The binaries build in the CI step are available in the releases (use at your own risk).

Architected for speed. Automated for easy. Monitoring and troubleshooting, transformed!

RDMA exmaple