🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman

A compact implementation of SGLang, designed to demystify the complexities of modern LLM serving systems.

Transformers-compatible library for applying various compression algorithms to LLMs for optimized deployment with vLLM

Milvus is a high-performance, cloud-native vector database built for scalable vector ANN search

The Generative AI Landscape - A Collection of Awesome Generative AI Applications

Use ChatGPT to summarize the arXiv papers. 全流程加速科研，利用chatgpt进行论文全文总结+专业翻译+润色+审稿+审稿回复

Papers from the computer science community to read and discuss.

Apache Pinot - A realtime distributed OLAP datastore

Jeff Dean's latency numbers plotted over time

Productive, portable, and performant GPU programming in Python.

The Fastest Distributed Database for Transactional, Analytical, and AI Workloads.

⏰ Agenticly track worldwide conference deadlines (Website, Python Cli, Wechat Applet)

Azure Cosmos TLA+ specifications

Zstandard - Fast real-time compression algorithm

Apache Arrow is the universal columnar format and multi-language toolbox for fast data interchange and in-memory analytics

MindSpore is a new open source deep learning training/inference framework that could be used for mobile, edge and cloud scenarios.

Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

Fast SHAP value computation for interpreting tree-based models

由图灵的猫开发，基于开源GPT2.0的初代创作型人工智能 | 可扩展、可进化

DNN connection pruning with Alternating Direction Method of Multipliers (ADMM)

An Introduction to Statistical Learning (James, Witten, Hastie, Tibshirani, 2013): Python code

Implementations of some Android Auto features as unofficial IDrive apps