Starred repositories
A JavaScript / TypeScript / Python / C# / PHP / Go cryptocurrency trading API with support for more than 100 bitcoin/altcoin exchanges
Production-tested AI infrastructure tools for efficient AGI development and community-driven innovation
📚LeetCUDA: Modern CUDA Learn Notes with PyTorch for Beginners🐑, 200+ CUDA/Tensor Cores Kernels, HGEMM, FA-2 MMA etc.🔥
Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud.
沉浸式双语网页翻译扩展 , 支持输入框翻译， 鼠标悬停翻译， PDF, Epub, 字幕文件, TXT 文件翻译 - Immersive Dual Web Page Translation Extension
EasyR1: An Efficient, Scalable, Multi-Modality RL Training Framework based on veRL
Suna - Open Source Generalist AI Agent
Ongoing research training transformer models at scale
modern AI for beginners
Rethinking RL Scaling for Vision Language Models: A Transparent, From-Scratch Framework and Comprehensive Evaluation Scheme
Super-Efficient RLHF Training of LLMs with Parameter Reallocation
魔法翻墙上网梯子推荐|SS、SSR、V2Ray、Trojan、Clash、winXray、Shadow| 魔法口令在速度和稳定性方面非常出色。需要注册通知订阅并作为软件使用，本仓库供你推荐好用的梯子。
🎡 Build Python wheels for all the platforms with minimal configuration.
LinkOS 公益运营的 docker.io、gcr.io、ghcr.io、quay.io、registry.k8s.io 镜像仓库加速服务。
A Datacenter Scale Distributed Inference Serving Framework
No fortress, purely open ground. OpenManus is Coming.
Train transformer language models with reinforcement learning.
This repository contains the Hugging Face Agents Course.
verl: Volcano Engine Reinforcement Learning for LLMs
DeepEP: an efficient expert-parallel communication library
FlashMLA: Efficient MLA decoding kernels
Optimized primitives for collective multi-GPU communication
A Flexible Framework for Experiencing Cutting-edge LLM Inference Optimizations
Large-scale, Informative, and Diverse Multi-round Chat Data (and Models)
The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.
xDiT: A Scalable Inference Engine for Diffusion Transformers (DiTs) with Massive Parallelism