Recover Protobuf descriptors from executables

Documentation for the iWork '13 File Format

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。

Accessible large language models via k-bit quantization for PyTorch.

A Flexible Framework for Experiencing Cutting-edge LLM Inference Optimizations

FORK of VLLM for AMD MI25/50/60. A high-throughput and memory-efficient inference and serving engine for LLMs

macOS file system notifications for Go.

提取微信聊天记录，将其导出成HTML、Word、Excel文档永久保存，对聊天记录进行分析生成年度聊天报告，用聊天数据训练专属于个人的AI聊天助手

llama.cpp fork with additional SOTA quants and improved performance

Cybertron: the home planet of the Transformers in Go

Get up and running with Llama 3.3, DeepSeek-R1, Phi-4, Gemma 2, and other large language models.

LLM inference in C/C++

Zero-copy I/O primitives and pipelines for Go. Linux-specific.

Manifest files for CasaOS Apps

OpenStack Object Storage (Swift)