标签：多机多卡

LocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required.

Milvus is a high-performance, cloud-native vector database built for scalable vector ANN search

Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

high-performance graph database for real-time use cases

A distributed, fast open-source graph database featuring horizontal scalability and high availability

Fault-tolerant, highly scalable GPU orchestration, and a machine learning framework designed for training models with billions to trillions of parameters

High-performance data engine for AI and multimodal workloads. Process images, audio, video, and structured data at any scale

CrateDB is a distributed and scalable SQL database for storing and analyzing massive amounts of data in near real-time, even with complex queries. It is PostgreSQL-compatible, and based on Lucene.

Distributed private networking

Lingvo

Distributed AI Model Training and LLM Fine-Tuning on Kubernetes

Agola: CI/CD Redefined

Open-source AI computer builds, from 2-GPU desktops to 8-GPU servers: CAD, BOM, BIOS and build guides. Get the case kit with PCIe risers, or ask us for a free fit check.

ArcadeDB Multi-Model Database, one DBMS that supports SQL, Cypher, Gremlin, HTTP/JSON, MongoDB and Redis. ArcadeDB is a conceptual fork of OrientDB, the first Multi-Model DBMS. ArcadeDB supports Vector Embeddings.

Community-driven, simple, yet powerful framework for fast, cost-effective distributed Compute over Data.

A HTTP Ruby API for Consul

Your AI intranet: network the computers you already own for inference and training.

Kubernetes operator for self-hosted LLM inference across a heterogeneous GPU fleet: NVIDIA CUDA, AMD Vulkan, and Apple Silicon Metal. Runtimes: llama.cpp, vLLM, TGI, mlx-server. Multi-GPU sharding, model caching, OpenAI-compatible endpoints. Apache-2.0, run across homelab and on-prem fleets, actively developed.

SSD-streaming inference engine for giant MoE models (Rust + CUDA). GLM 5.2 743B at 2 tok/s and Hy3 295B at 7 tok/s on two consumer 16GB GPUs. Zero-config multi-GPU: measures PCIe bandwidth, places attention and hot experts where they fit.