LMDeploy is a toolkit for compressing, deploying, and serving LLMs.
- cuda-kernels
- deepspeed
- fastertransformer
- llm-inference
108,094 visible repositories in the index
97–120 of 665 · Most stars
LMDeploy is a toolkit for compressing, deploying, and serving LLMs.
Evidently is an open-source ML and LLM observability framework. Evaluate, test, and monitor any AI-powered system or data pipeline. From tabular data to Gen AI. 100+ metrics.
Stylish, intuitive and user-friendly prompts. Used by eslint, webpack, yarn, pm2, pnpm, RedwoodJS, FactorJS, salesforce, Cypress, Google Lighthouse, Generate, tencent cloudbase, lint-staged, gluegun, hygen, hardhat, AWS Amplify, GitHub Actions Toolkit, @airbnb/nimbus, and more! Please follow Enquirer's author: https://github.com/jonschlinkert
Open source inference engine that tunes its kernels on your hardware to find the fastest way to run each model. 2x faster than Ollama. Works on Apple Silicon, NVIDIA, AMD, Intel, or just a CPU.
Implementation of RLHF (Reinforcement Learning with Human Feedback) on top of the PaLM architecture. Basically ChatGPT but with PaLM
Infrastructure for continually self‑improving agents
The official repository for ERNIE 4.5 and ERNIEKit – its industrial-grade development toolkit based on PaddlePaddle.
TranslatedSelf-hosted knowledge agent platform for RAG, knowledge graphs and multi-agent workflows. Yuxi = Cloud Agents + Knowledge RAG, Self-hosted knowledge agent platform for RAG, knowledge graphs and multi-agent workflows.
ClawX is a desktop app that provides a graphical interface for OpenClaw AI agents. It turns CLI-based AI orchestration into a desktop experience without using the terminal. China website is https://clawx.com.cn.
A pixel office for your OpenClaw: turn invisible work states into a cozy little space with characters, daily notes, and guest agents. Code under MIT; art assets for non-commercial learning only.
Optimize prompts, code, and more with AI-powered Reflective Optimization
Official release of InternLM series (InternLM, InternLM2, InternLM2.5, InternLM3).
PDF GPT allows you to chat with the contents of your PDF file by using GPT capabilities. The most effective open source solution to turn your pdf files in a chatbot!
TranslatedChinese LLaMA-2 & Alpaca-2 LLMs with 64K long context models
Self-hosted TypeScript agent runtime with durable approvals and verifiable run records. Own it, approve it, audit it.
Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.
Open Source Neural Machine Translation and (Large) Language Models in PyTorch
Postgres with GPUs for ML/AI apps.
One UI is all done with chatgpt web, midjourney, gpts,suno,luma,runway,viggle,flux,ideogram,realtime,pika,udio; Simultaneous support Web / PWA / Linux / Win / MacOS platform
Efficient Triton Kernels for LLM Training
TranslatedFirefly: a large model training tool that supports training large models such as Qwen2.5, Qwen2, Yi1.5, Phi-3, Llama3, Gemma, MiniCPM, Yi, Deepseek, Orion, Xverse, Mixtral-8x7B, Zephyr, Mistral, Baichuan2, Llma2, Llama, Qwen, Baichuan, ChatGLM2, InternLM, Ziya2, Vicuna, Bloom, etc.
Code for the paper "Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer"
Translated非线智能 NoneLinear (Non-linear Intelligence) - ReLE evaluation: capability evaluation of Chinese AI large models (continuously updated): it currently covers 374 large models, including commercial models such as chatgpt, gpt-5.4, Google gemini-3.1-pro, Claude-4.6, 文心 ERNIE-X1.1, ERNIE-5.0, qwen3.6-max, qwen3.6-plus, Baichuan, iFlytek Spark, and SenseTime senseChat, as well as open-source large models such as step3.5-flash, kimi-k2.6, ernie4.5, MiniMax-M2.7, deepseek-v4, Qwen3.6, llama4, Zhipu GLM-5.1, MiMo-V2, LongCat, gemma4, and mistral. It provides not only leaderboards but also a large model defect library with more than 2,000,000 entries! This makes it convenient for the broad community to research, analyze, and improve large models.
An open, programmable decision layer for models and compute.