Friendli: the fastest serving engine for generative AI

🦋 A personal research and development (R&D) lab that facilitates the sharing of knowledge.

The easiest way to serve AI/ML models in production - Build Model Inference Service, LLM APIs, Multi-model Inference Graph/Pipelines, LLM/RAG apps, and more!

A high-throughput and memory-efficient inference and serving engine for LLMs

Scalable and flexible workflow orchestration platform that seamlessly unifies data, ML and analytics stacks.

Production Grade Nifi & Nifi Registry. Deploy for VM (Virtual Machine) with Terraform + Ansible, Helm & Helmfile for Kubernetes (EKS)

🔥 A tool for visualizing and tracking your machine learning experiments. This repo contains the CLI and Python API.

Extensible Python SDK for developing Flyte tasks and workflows. Simple to get started and learn and highly extensible.

AI Observability & Evaluation

Examples of models deployable with Truss

AIプロダクト開発のための Tips 集

FEDML - The unified and scalable ML library for large-scale distributed training, model serving, and federated learning. FEDML Launch, a cross-cloud scheduler, further enables running any AI jobs on any GPU cloud or on-premise cluster. Built on this library, TensorOpera AI (https://TensorOpera.ai) is your generative AI platform at scale.

An orchestration platform for the development, production, and observation of data assets.

A data-centric AI Platform for Building & Using AI

Determined is an open-source machine learning platform that simplifies distributed training, hyperparameter tuning, experiment tracking, and resource management. Works with PyTorch and TensorFlow.

PostgreSQL vector database extension for building AI applications

Qdrant - High-performance, massive-scale Vector Database for the next generation of AI. Also available in the cloud https://cloud.qdrant.io/

Workflow Engine for Kubernetes

Aim 💫 — An easy-to-use & supercharged open-source experiment tracker.

Turns Data and AI algorithms into production-ready web applications in no time.