Awesome GitHub RepositoriesMulti-Node

mistral.rs is an inference engine for large language models that runs locally and exposes models behind OpenAI and Anthropic-compatible APIs. It serves as a multi-model serving platform, capable of loading several models in a single server process with per-request routing and on-demand loading and unloading. The engine supports multimodal inference, processing text alongside images, video, audio, and speech inputs, and includes a quantized model deployment runtime that reduces memory use and speeds up inference on consumer hardware. The project distinguishes itself through an agentic tool exe

Dynamo is a distributed inference orchestration platform designed for large language models. It functions as a system to coordinate prefill and decode phases across GPU nodes, utilizing a multi-backend runtime adapter to connect engines like vLLM and TensorRT-LLM through a unified block-oriented memory interface. An OpenAI-compatible API server provides the frontend for integration with existing tools and clients. The project is distinguished by its disaggregated serving architecture, which separates prompt processing and token generation onto independent GPU pools to optimize throughput and

FlashInfer is a library of high-performance GPU kernels purpose-built for accelerating large language model inference. It provides optimized implementations for attention operations (including flash attention, page attention, multi-head latent attention, and cascade attention) using paged key-value caches, fused kernel composition, and just-in-time compilation. The library also includes specialized kernels for mixture-of-experts layers, block-scaled low-precision quantization (FP8, FP4), and distributed collective communication. What distinguishes FlashInfer is its fused all-reduce communicat

NCCL 是一个高性能通信库和分布式 GPU 计算框架，专为在单节点或多节点系统中的多个 GPU 之间执行集合和点对点数据交换而设计。它充当 RDMA GPU 传输层和内存编排器，为分布式 GPU 训练和推理提供高带宽的数据和模型梯度同步。 该库的特色在于能够直接从 GPU 内核执行通信原语，将主机 CPU 从关键路径中移除。它利用拓扑感知路径选择来优化数据移动，并采用包括 InfiniBand 和 NVLink 在内的基于 RDMA 的网络传输，以实现设备跨不同物理节点之间的零拷贝内存访问。 该项目涵盖了广泛的集合通信模式，包括归约（Reductions）、广播（Broadcasts）、收集（Gathers）和全对全交换（All-to-all exchanges），以及点对点远程内存访问。它提供全面的通信器管理，用于初始化、分区和调整 GPU 组大小，以及用于注册缓冲区和协调共享设备内存的专用内存管理。 该系统包括一套用于健康跟踪、诊断日志记录和实时事件监控的监控与可观测性工具，以及用于机器学习框架、CUDA Graphs、MPI 和 Python 的集成接口。

Distributed-llama is a distributed inference engine and command line tool for running large language models across multiple networked machines. It functions as a compute cluster manager that coordinates worker nodes to share the computational load of a single model. The system utilizes tensor parallelism to shard model weights across different hosts, allowing the execution of models that exceed the memory capacity of a single piece of hardware. It includes a dedicated format converter to transform standard model files into a compatible binary layout optimized for distributed loading. The eng