Awesome-LLMOps

🎉 An awesome & curated list of best LLMOps tools. But more about LLMOps.

LLMOps

Name	Stars	Release	Contributors	About	Tag
BentoML				Build Production-Grade AI Applications
Dify				One API for plugins and datasets, one interface for prompt engineering and visual operation, all for creating powerful AI applications
FastChat				An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.
Flowise				Drag & drop UI to build your customized LLM flow
Haystack				🔍 LLM orchestration framework to build customizable, production-ready LLM applications. Connect components (models, vector DBs, file converters) to pipelines or agents that can interact with your data. With advanced retrieval methods, it's best suited for building RAG, question answering, semantic search or conversational agent chatbots.
LangChain				⚡ Building applications with LLMs through composability ⚡
LiteLLM				lightweight package to simplify LLM API calls - Azure, OpenAI, Cohere, Anthropic, Replicate. Manages input/output translation
LLaMa-Factory				Easy-to-use LLM fine-tuning framework (LLaMA, BLOOM, Mistral, Baichuan, Qwen, ChatGLM)
LlamaIndex				LlamaIndex is a data framework for your LLM applications
Mem0				The memory layer for Personalized AI
Open WebUI				User-friendly WebUI for LLMs (Formerly Ollama WebUI)
PrivateGPUT				Interact with your documents using the power of GPT, 100% privately, no data leaks
Swift				SWIFT supports training(PreTraining/Fine-tuning/RLHF), inference, evaluation and deployment of 350+ LLMs and 90+ MLLMs (multimodal large models).

MLOps

Name	About	Tag
Flyte	Scalable and flexible workflow orchestration platform that seamlessly unifies data, ML and analytics stacks.
Kubeflow	Machine Learning Toolkit for Kubernetes	cloud
Metaflow	🚀 Build and manage real-life data science projects with ease!
MLflow	Open source platform for the machine learning lifecycle
Seldon-Core	An MLOps framework to package, deploy, monitor and manage thousands of production machine learning models.	cloud
ZenML	ZenML 🙏: Build portable, production-ready MLOps pipelines. https://zenml.io.

Inference

Name	About	Tag
DeepSpeed-MII	MII makes low-latency and high-throughput inference possible, powered by DeepSpeed.
Inference	A fast, easy-to-use, production-ready inference server for computer vision supporting deployment of many popular model architectures and fine-tuned models.	vision
ipex-llm	Accelerate local LLM inference and finetuning (LLaMA, Mistral, ChatGLM, Qwen, Baichuan, Mixtral, Gemma, Phi, MiniCPM, etc.) on Intel CPU and GPU (e.g., local PC with iGPU, discrete GPU such as Arc, Flex and Max); seamlessly integrate with llama.cpp, Ollama, HuggingFace, LangChain, LlamaIndex, GraphRAG, DeepSpeed, vLLM, FastChat, Axolotl, etc.	device
llmaz	☸️ Effortlessly serve state-of-the-art LLMs on Kubernetes.
LMDeploy	LMDeploy is a toolkit for compressing, deploying, and serving LLMs.
MaxText	A simple, performant and scalable Jax LLM!	Jax
llama.cpp	LLM inference in C/C++	device
MInference	To speed up Long-context LLMs' inference, approximate and dynamic sparse calculate the attention, which reduces inference latency by up to 10x for pre-filling on an A100 while maintaining accuracy.
MLC LLM	Universal LLM Deployment Engine with ML Compilation
MLServer	MLServer aims to provide an easy way to start serving your machine learning models through a REST and gRPC interface, fully compliant with KFServing's V2 Dataplane spec.
Nanoflow	A throughput-oriented high-performance serving framework for LLMs
Ollama	Get up and running with Llama 3, Mistral, Gemma 2, and other large language models.	device
OpenLLM	Operating LLMs in production
OpenVINO	OpenVINO™ is an open-source toolkit for optimizing and deploying AI inference
Ratchet	A cross-platform browser ML framework.	browser
RayServe	Ray is a unified framework for scaling AI and Python applications. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.
RouteLLM	A framework for serving and evaluating LLM routers - save LLM costs without compromising quality.	cost
SGLang	SGLang is a structured generation language designed for large language models (LLMs). It makes your interaction with models faster and more controllable.
transformers.js	State-of-the-art Machine Learning for the web. Run 🤗 Transformers directly in your browser, with no need for a server!	browser
Triton Inference Server	The Triton Inference Server provides an optimized cloud and edge inferencing solution.
TensorRT-LLM	TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs.
Text Generation Inference	Large Language Model Text Generation Inference
vLLM	A high-throughput and memory-efficient inference and serving engine for LLMs
web-llm	A high-throughput and memory-efficient inference and serving engine for LLMs	browser
zml	High performance AI inference stack. Built for production.

Training

Name	Stars	Release	Contributors	About	Tag
ColossalAI				Making large AI models cheaper, faster and more accessible
Ludwig				Low-code framework for building custom LLMs, neural networks, and other AI models
MLX				MLX: An array framework for Apple silicon

FineTune

Name	Stars	Release	Contributors	About	Tag
Axolotl				Go ahead and axolotl questions
torchtune				A Native-PyTorch Library for LLM Fine-tuning
unsloth				Finetune Llama 3, Mistral, Phi & Gemma LLMs 2-5x faster with 80% less memory

Agent

Name	Stars	Release	Contributors	About	Tag
AutoGPT				An experimental open-source attempt to make GPT-4 fully autonomous.
MetaGPT				🌟 The Multi-Agent Framework: Given one line Requirement, return PRD, Design, Tasks, Repo
Swarm				Framework for building, orchestrating and deploying multi-agent systems. Managed by OpenAI Solutions team. Experimental framework.
XAgent				An Autonomous LLM Agent for Complex Task Solving

Evaluation

Name	About	Tag
AgentBench	A Comprehensive Benchmark to Evaluate LLMs as Agents
lm-evaluation-harness	A framework for few-shot evaluation of language models.
LongBench	LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding	long-context

DB Store

Name	About	Tag
chroma	the AI-native open-source embedding database	vector
deeplake	Database for AI. Store Vectors, Images, Texts, Videos, etc. Use with LLMs/LangChain. Store, query, version, & visualize any AI data. Stream data in real-time to PyTorch/TensorFlow. https://activeloop.ai
Faiss	A library for efficient similarity search and clustering of dense vectors.	vector
milvus	A cloud-native vector database, storage for next generation AI applications	cloud,vector
weaviate	Weaviate is an open-source vector database that stores both objects and vectors, allowing for the combination of vector search with structured filtering with the fault tolerance and scalability of a cloud-native database.	cloud,vector

Observation

Name	Stars	Release	Contributors	About	Tag
OpenLLMetry				Open-source observability for your LLM application, based on OpenTelemetry
Helicone AI				🧊 The open-source LangSmith alternative for logging, monitoring, and debugging AI applications.
phoenix				ML Observability in a Notebook - Uncover Insights, Surface Problems, Monitor, and Fine Tune your Generative LLM, CV and Tabular Models
wandb				🔥 A tool for visualizing and tracking your machine learning experiments. This repo contains the CLI and Python API.

Alignment

Name	Stars	Release	Contributors	About	Tag
OpenRLHF				An Easy-to-use, Scalable and High-performance RLHF Framework (70B+ PPO Full Tuning & Iterative DPO & LoRA & Mixtral)
Self-RLHF				Safe RLHF: Constrained Value Alignment via Safe Reinforcement Learning from Human Feedback