-
In Cloud
- Chengdu
- https://johng.cn
Starred repositories
an open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM
Run Slurm as a Kubernetes scheduler. A Slinky project.
The official Go SDK for Model Context Protocol servers and clients. Maintained in collaboration with Google.
Examples of my Claude Code infrastructure with skill auto-activation, hooks, and agents
Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.
FastGPT is a knowledge-based platform built on the LLMs, offers a comprehensive suite of out-of-the-box capabilities such as data processing, RAG retrieval, and visual AI workflow orchestration, le…
Helm Chart & Documentation for deploying JupyterHub on Kubernetes
🗂 The perfect Front-End Checklist for modern websites and meticulous developers
Kubernetes-native AI serving platform for scalable model serving.
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
AIInfra(AI 基础设施)指AI系统从底层芯片等硬件,到上层软件栈支持AI大模型训练和推理。
🦜🔗 The platform for reliable agents.
GoFly快速开发框架基于Gin快速开发框架,能快速搭建应用、框架底层完善、丰富代码仓插件、快速开发数据大屏、物联网平台、OA流程审批、工作流引擎、商城、微信管理后台等。api文档管理并一键生成api接口代码,一键生成 CRUD前后端代码丰富组件,基于 Gin和 Vue3的Arco Design的快速后台开发框架,基于JWT接口验证和Auth验证的权限管理系统,附件管理系统,天生支持saas…
cube studio开源云原生一站式机器学习/深度学习/大模型AI平台,mlops算法链路全流程,算力租赁平台,notebook在线开发,拖拉拽任务流pipeline编排,多机多卡分布式训练,超参搜索,推理服务VGPU虚拟化,边缘计算,标注平台自动化标注,deepseek等大模型sft微调/奖励模型/强化学习训练,vllm/ollama/mindie大模型多机推理,私有知识库,AI模型市场…
Virtualized Elastic KV Cache for Dynamic GPU Sharing and Beyond
A high-performance distributed file system designed to address the challenges of AI training and inference workloads.
Tensor Fusion is a state-of-the-art GPU virtualization and pooling solution designed to optimize GPU cluster utilization to its fullest potential.
Kubernetes WithOut Kubelet - Simulates thousands of Nodes and Clusters.
A modern GUI client based on Tauri, designed to run in Windows, macOS and Linux for tailored proxy experience
Label Studio is a multi-type data labeling and annotation tool with standardized output format
HAMi-core compiles libvgpu.so, which ensures hard limit on GPU in container
SGLang is a fast serving framework for large language models and vision language models.
Build and run containers leveraging NVIDIA GPUs
Device-plugin for volcano vgpu which support hard resource isolation