verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework

Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen3.6, GPT-OSS, Llama, and more!

Post-training with Tinker

A next.js web application that integrates AI capabilities with draw.io diagrams. This app allows you to create, modify, and enhance diagrams through natural language commands and AI-assisted visual…

slime is an LLM post-training framework for RL Scaling.

OpenTinker is an RL-as-a-Service infrastructure for foundation models

Checkpoint-engine is a simple middleware to update model weights in LLM inference engines

TurboDiffusion: 100–200× Acceleration for Video Diffusion Models

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

EasyR1: An Efficient, Scalable, Multi-Modality RL Training Framework based on veRL

An Efficient and User-Friendly Scaling Library for Reinforcement Learning with Large Language Models

FaaSNet: Scalable and Fast Provisioning of Custom Serverless Container Runtimes at Alibaba Cloud Function Compute (USENIX ATC'21)

High-quality and streaming Speech-to-Speech interactive agent in a single file. 只用一个文件实现的流式全双工语音交互原型智能体！

A high-performance inference system for large language models, designed for production environments.

Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.

KV cache store for distributed LLM inference

Run LLMs with MLX

LMCache: Supercharge Your LLM with the Fastest KV Cache Layer

A high-performance distributed file system designed to address the challenges of AI training and inference workloads.

Production-tested AI infrastructure tools for efficient AGI development and community-driven innovation

High-performance Python librarys for connecting AI/ML frameworks with OSS storage.

主要记录大语言大模型（LLMs） 算法（应用）工程师相关的知识及面试题

A self-learning tutorail for CUDA High Performance Programing.

cricket is a virtualization solution for GPUs

Disaggregated serving system for Large Language Models (LLMs).

A Flexible Framework for Experiencing Heterogeneous LLM Inference/Fine-tune Optimizations

SGLang is a high-performance serving framework for large language models and multimodal models.

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…