MatheMatrix/sglang
SGLang is a high-performance serving framework for large language models and multimodal models.
Cloud engineer, working at @zstackio Sometimes I act as a robot
SGLang is a high-performance serving framework for large language models and multimodal models.
ZStack - the open-source IaaS software http://zstack.org
2018年春季课程学习资料汇总
Cloud native, ultra-high performance AI&API gateway, LLM API management, distribution system, open platform, supporting all AI APIs.🦄云原生、超高性能 AI&API网关,LLM API 管理、分发系统、开放平台,支持所有AI API,不限于OpenAI、Azure、Anthropic Claude、Google Gemini、DeepSeek、字节豆包、ChatGLM、文心一言、讯飞星火、通义千问、360 智脑、腾讯混元等主流模型,统一 API 请求和返回,API申请与审批,调用统计、负载均衡、多模型灾备。一键部署,开箱即用。
🚀 Next Generation AI One-Stop Internationalization Solution. 🚀 下一代 AI 一站式 B/C 端解决方案,支持 OpenAI,Midjourney,Claude,讯飞星火,Stable Diffusion,DALL·E,ChatGLM,通义千问,腾讯混元,360 智脑,百川 AI,火山方舟,新必应,Gemini,Moonshot 等模型,支持对话分享,自定义预设,云端同步,模型市场,支持弹性计费和订阅计划模式,支持图片解析,支持联网搜索,支持模型缓存,丰富美观的后台管理与仪表盘数据统计。
export wiz notes to md
AI Manus is a general-purpose AI Agent system that supports running various tools and operations in a sandbox environment.
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
Agents and tools for project ZStack http://zstack.org
基于大模型(DeepSeek,OpenAI等)的 GitLab 自动代码审查工具;支持钉钉/企业微信/飞书推送消息和生成日报;支持Docker部署;可视化 Dashboard。
Enjoy the magic of Diffusion models!
A powerful tool for creating fine-tuning datasets for LLM
Simplified
⚡️ Free Next.js responsive landing page template for SaaS products made using JAMStack architecture.
Curve meetup slides
Connect AI models (like ChatGPT-3.5/4.0, Baidu Yiyan, New Bing, Bard) to apps (like Wechat, public account, DingTalk, Telegram, QQ). 将 ChatGPT、必应、文心一言、谷歌Bard 等对话模型连接各类应用,如微信、公众号、QQ、Telegram、Gmail、Slack、Web、企业微信、飞书、钉钉等。
Awesome Digital Human
An OpenAI Completions API compatible server for NLP transformers models
A high-throughput and memory-efficient inference and serving engine for LLMs
Calculate token/s & GPU memory requirement for any LLM. Supports llama.cpp/ggml/bnb/QLoRA quantization
Self-hosted huggingface mirror service.
Device-plugin for volcano vgpu which support hard resource isolation
Real time streaming digital human based on nerf
OpenAIOS vGPU scheduler for Kubernetes is originated from the OpenAIOS project to virtualize GPU device memory.
HAMi-core compiles libvgpu.so, which ensures hard limit on GPU in container