how to optimize some algorithm in cuda.

My learning notes/codes for ML SYS.

A Portable Graphic Format for TeX

🚀 Awesome System for Machine Learning ⚡️ AI System Papers and Industry Practice. ⚡️ System for Machine Learning, LLM (Large Language Model), GenAI (Generative AI). 🍻 OSDI, NSDI, SIGCOMM, SoCC, MLSy…

Repo for paper "M-MAD: Multidimensional Multi-Agent Debate for Advanced Machine Translation Evaluation"

This is the homepage of a new book entitled "Mathematical Foundations of Reinforcement Learning."

A library for advanced large language model reasoning

This repository collects some codes that encapsulates commonly used algorithms in the field of machine learning. Most of them are based on Numpy, Pandas or Torch. You can deepen your understanding …

An Easy-to-use, Scalable and High-performance RLHF Framework (70B+ PPO Full Tuning & Iterative DPO & LoRA & RingAttention & RFT)

A curated list of awesome Deep Reinforcement Learning resources.

An Open-source Framework for Data-centric, Self-evolving Autonomous Language Agents

The solution and dataset of Team ZJU_AI4H in Amazon KDDCUP 2024 (Track 2 Top 2; Track 5 Top 5)

Codes for our paper "ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate"

🤖 AgentVerse 🪐 is designed to facilitate the deployment of multiple LLM-based agents in various applications, which primarily provides two frameworks: task-solving and simulation

[EMNLP'24] Code and data for paper "Med-MoE: Mixture of Domain-Specific Experts for Lightweight Medical Vision-Language Models"

LDB: A Large Language Model Debugger via Verifying Runtime Execution Step by Step

Easy, fast, and cheap pretrain,finetune, serving for everyone

Evaluate your LLM's response with Prometheus and GPT4 💯

A recipe for online RLHF and online iterative DPO.

Code and data realeases for the paper -- TasTe: Teaching Large Language Models to Translate through Self-Reflection

[EMNLP'24] Code and data for paper "Ladder: A Model-Agnostic Framework Boosting LLM-based Machine Translation to the Next Level"

Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.

Dify is an open-source LLM app development platform. Dify's intuitive interface combines AI workflow, RAG pipeline, agent capabilities, model management, observability features and more, letting yo…

General technology for enabling AI capabilities w/ LLMs and MLLMs

中文LLaMA&Alpaca大语言模型+本地CPU/GPU训练部署 (Chinese LLaMA & Alpaca LLMs)

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）