Stars
The Cloud Sandbox Built for AI Agents
DashInfer is a native LLM inference engine aiming to deliver industry-leading performance atop various hardware architectures, including CUDA, x86 and ARMv9.
Clean, Robust, and Unified PyTorch implementation of popular Deep Reinforcement Learning (DRL) algorithms (Q-learning, Duel DDQN, PER, C51, Noisy DQN, PPO, DDPG, TD3, SAC, ASL)
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）
用于从头预训练+SFT一个小参数量的中文LLaMa2的仓库；24G单卡即可运行得到一个具备简单中文问答能力的chat-llama2.
FinRL®: Financial Reinforcement Learning. 🔥
TradeMaster is an open-source platform for quantitative trading empowered by reinforcement learning 🔥 ⚡ 🌈
SGLang is a high-performance serving framework for large language models and multimodal models.
Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.
Simple connector to Binance Public API
Official Documentation for the Binance Spot APIs and Streams
📚A curated list of Awesome LLM/VLM Inference Papers with Codes: Flash-Attention, Paged-Attention, WINT8/4, Parallelism, etc.🎉
TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. Tensor…
The Startup CTO's Handbook, a book covering leadership, management and technical topics for leaders of software engineering teams
C++ Implementation of PyTorch Tutorials for Everyone
《面向开发者的 ChatGPT 提示词工程》非官方版中英双语字幕 Unofficial subtitles of "ChatGPT Prompt Engineering for Developers"
Code and documentation to train Stanford's Alpaca models, and generate the data.
BELLE: Be Everyone's Large Language model Engine（开源中文对话大模型）
Finetuning Large Language Models on One Consumer GPU in 2 Bits
The paper list of the 86-page SCIS cover paper "The Rise and Potential of Large Language Model Based Agents: A Survey" by Zhiheng Xi et al.
Code and models for ICML 2024 paper, NExT-GPT: Any-to-Any Multimodal Large Language Model
ChatDev 2.0: Dev All through LLM-powered Multi-Agent Collaboration
AISystem 主要是指AI系统，包括AI芯片、AI编译器、AI推理和训练框架等AI全栈底层技术
An MLIR-based compiler framework bridges DSLs (domain-specific languages) to DSAs (domain-specific architectures).
AITemplate is a Python framework which renders neural network into high performance CUDA/HIP C++ code. Specialized for FP16 TensorCore (NVIDIA GPU) and MatrixCore (AMD GPU) inference.
Fast and memory-efficient exact attention