订阅转换合并，节点可用性，测速，重命名，导出为clash.meta/clash/base64/qx等等所有格式的订阅工具

A Datacenter Scale Distributed Inference Serving Framework

Make customized Alpine Linux rootfs (base image) for containers

Docker Official Image packaging for Busybox

A high-performance distributed file system designed to address the challenges of AI training and inference workloads.

DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling

FlashMLA: Efficient MLA decoding kernels

A professional cross-platform SSH/Sftp/Shell/Telnet/Tmux/Serial terminal.

📚A curated list of Awesome LLM/VLM🔥 Inference Papers with codes: WINT8/4, FlashAttention, PagedAttention, MLA, Parallelism etc.

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

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

GPT-SoVITS纯Rust编译推理代码（Demo工程代码）：包含文本前端（中英文混合输入解析）、onnx模型推理、ffmpeg底层API实现的音频输出及变速、音频实时合成实时播放等

一键DD/重装脚本 (One-click reinstall OS on VPS)

大模型基础: 一文了解大模型基础知识

🛠「Watt Toolkit」是一个开源跨平台的多功能 Steam 工具箱。

DashInfer is a native LLM inference engine aiming to deliver industry-leading performance atop various hardware architectures, including CUDA, x86 and ARMv9.

Universal cross-platform tokenizers binding to HF and sentencepiece

fastllm是c++实现，后端无依赖（仅依赖CUDA，无需依赖PyTorch）的高性能大模型推理库。 可实现单4090推理DeepSeek R1 671B INT4模型，单路可达20+tps。

Always updated offsets.

Counter-Strike: 2 Offset Dumper

open-source pen-test [CS:GO/CS2/Apex]

Detailed Instructions on the creation of custom/modified DMA (attack) Firmware based on pcileech-fpga

pcileech-fpga with wireless card emulation

This a small cheat menu for Sword With Sauce (a UE4 game) that I made in a week or so. The reason why I am sharing the project is that it is probably one of the best sources to learn UE game hackin…

CSGO ESP, Web Radar and Grenade helper using kernel hook for km-um communication

Internal cheat for Realm Royale. The game engine is UE3.

DMA Cheat For COD4X

Borderlands2 hacker use UE3 SDK