Open-source alternatives to Distributed Llama

zml is a machine learning model compiler and cross-platform inference engine that transforms model descriptions into optimized executable binaries for specific hardware accelerators. It functions as a model deployment toolkit and hardware-agnostic orchestrator, utilizing a tensor-based architecture definition to provide strong type checking during the compilation process. The project distinguishes itself through the ability to shard tensors and distribute large-scale AI workloads across a logical mesh of multiple devices. It further supports the remote model lifecycle by authenticating and do

fastllm is a set of specialized software components for model weight conversion, Mixture-of-Experts runtimes, and tensor parallelism. It provides an OpenAI compatible API server to expose large language model capabilities through a standardized request format. The project features a tensor parallelism framework that splits computational workloads across multiple GPUs to accelerate execution. It includes a dedicated runtime optimized for Mixture-of-Experts architectures and a quantization tool to convert model weights into lower precision formats to reduce memory usage and increase throughput.

BigDL is a PyTorch acceleration framework and distributed inference engine designed for large language models. It provides a toolkit for running models on Intel hardware, integrating quantization tools and libraries for parameter-efficient fine-tuning. The project distinguishes itself through the use of pipeline parallelism to distribute model workloads across multiple hardware accelerators. It utilizes low-bit integer quantization and speculative decoding to reduce memory footprints and decrease text generation latency. The system covers broad capabilities in model optimization, including w

This project is a structured learning curriculum and technical reference for mastering deep learning with TensorFlow. It provides a comprehensive guide for building, training, and deploying neural networks, combining theoretical fundamentals with practical implementation examples. The repository distinguishes itself by covering the end-to-end machine learning workflow, from low-level tensor mathematics and linear algebra to the creation of complex model architectures. It includes specific guidance on developing data pipelines for diverse data types, such as images, text, and time-series seque

This project is a large language model inference library and framework designed to run models for text generation, problem solving, and coding assistance. It includes a multimodal framework for processing combined image and text inputs and a tool-use implementation that enables the execution of external functions based on model reasoning. The system features a distributed GPU inference engine that spreads large model workloads across multiple graphics processors to increase processing speed and meet memory requirements. It also provides containerized model deployment through pre-packaged imag

MiniCPM is a collection of small language models designed for local, on-device deployment in resource-constrained environments. The project focuses on running dense Transformer models on consumer hardware, including GPUs, CPUs, and Apple Silicon, without requiring custom code forks. The project distinguishes itself through heavy optimization for edge hardware, utilizing quantized weight compression in GGUF and MLX formats to reduce memory overhead. It implements advanced inference techniques such as speculative sampling and radix-tree prefix caching to accelerate generation speed and throughp

CTranslate2 is a C++ inference engine and runtime for Transformer models, designed to execute models on both CPU and GPU with optimizations for speed and memory efficiency. It functions as a model format converter, quantization tool, and REST API server, enabling deployment of neural machine translation, automatic speech recognition, and text generation models. The engine distinguishes itself through a suite of runtime optimizations including layer fusion, weight-matrix quantization, batch-by-length grouping, and a caching allocator that reuses GPU memory. It supports tensor-parallel model di

lmdeploy is a high-performance inference engine and deployment framework for large language models and vision models. It functions as a multi-modal model server and compression toolkit designed to serve models with high throughput and low latency. The system enables the distribution of model services across multiple machines using request-based load balancing and tensor parallelism. It includes specialized tools for model quantization and compression to reduce the memory footprint of weights and caches. The framework covers broad capability areas including production deployment, distributed

Exo is a distributed inference engine designed to run machine learning models across local hardware. It functions as a network orchestration layer that automatically discovers available devices to form a unified computing cluster, allowing users to scale artificial intelligence workloads by distributing computational tasks across multiple machines. The platform distinguishes itself through its ability to manage the entire lifecycle of local models while providing a standardized gateway for external applications. By translating local model outputs into industry-standard formats, it enables exi

PowerInfer is a high-performance local large language model inference engine and sparse inference framework. It provides a runtime for executing models on consumer-grade hardware, utilizing a GPU acceleration backend to optimize tensor operations for graphics processors. The system distinguishes itself through a sparse inference framework that increases generation speed by skipping computations based on activation sparsity in model weights. It includes a GGUF model converter for transforming weights and metadata into a unified binary format, as well as an OpenAI API compatible server for inte

This project provides a comprehensive architectural blueprint and implementation set for building a platform-as-a-service on Kubernetes. It serves as a technical resource for deploying container orchestration environments, managing the full software development lifecycle, and integrating a complete DevOps toolchain. The implementation emphasizes automated software delivery through the integration of build and delivery pipelines, private container registries, and distributed configuration systems. It enables the decoupling of application settings from images via a centralized configuration man

Skynet is a distributed game server framework designed for building scalable online game backends. It utilizes distributed actor-based clusters and real-time network communication to manage high-concurrency session coordination across multiple nodes. The framework includes a cluster management orchestrator for coordinating services via cluster-wide messaging and dynamic configuration updates. It features a multi-protocol network gateway supporting TCP, UDP, and WebSockets, alongside a data encoding layer using BSON and Sproto serialization for efficient information transfer between distribute

ExecuTorch is a lightweight C++ runtime for deploying PyTorch models on mobile, embedded, and edge hardware. It provides an ahead-of-time compilation pipeline that exports, quantizes, and lowers model graphs into compact serialized programs, then executes them through a minimal runtime with hardware acceleration and on-device large language model inference capabilities. The project distinguishes itself through a hardware accelerator delegate system that partitions model subgraphs and offloads computation to specialized backends including NPUs, GPUs, and DSPs from Apple, Arm, Intel, MediaTek,

mini-sglang is a collection of tools for large language model inference, serving as an OpenAI-compatible inference server, a memory-efficient prefill engine, and a tensor parallelism runtime. It also functions as a local batch processing engine for offline benchmarking and ablation studies. The project focuses on acceleration and memory management through a KV cache manager that reuses precomputed caches for shared request prefixes. It handles large model workloads by distributing tasks across multiple GPUs and manages peak memory consumption by splitting long input sequences into smaller chu

Lorax is a GPU-accelerated inference server and multi-adapter engine designed for serving large language models. It functions as a high-throughput system capable of deploying models via Kubernetes and managing the dynamic swapping of Low-Rank Adaptation adapters per request. The server distinguishes itself through multi-adapter dynamic batching, which allows requests using different adapter weights to be processed in a single GPU forward pass. It employs just-in-time adapter loading and weighted adapter merging to maximize throughput and enable multi-tasking without sacrificing performance.

Chitu is a distributed serving platform and orchestrator for large language model inference. It functions as a compute manager designed to deploy and scale model workloads across diverse hardware architectures, including GPUs, CPUs, and heterogeneous hardware clusters. The platform enables model deployment across a wide range of targets, including NVIDIA GPUs, regional chipsets, and legacy hardware. It manages the execution of models across these varying environments to increase available computing capacity and optimize resource utilization. The system includes capabilities for distributed i

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

LiteRT is a runtime and API for executing machine learning and generative AI models on mobile, desktop, and IoT hardware. It consists of an inference engine and a specialized environment for running quantized large language and diffusion models locally on edge hardware. The system includes an ahead-of-time model compiler that translates models into hardware-specific bytecode to reduce startup latency and memory overhead. It provides a unified interface for Neural Processing Units with automatic fallback routing to CPUs or GPUs when specific subgraph support is unavailable. An edge model conve

Sglang is a high-performance inference engine and serving system designed for large language and multimodal models. It provides a programmable interface for orchestrating complex generation workflows, enabling developers to coordinate multi-turn dialogues, tool invocations, and reasoning chains through a domain-specific language. The platform is built to support production-scale deployments, offering an OpenAI-compatible API that allows for integration with existing application ecosystems. The system distinguishes itself through a disaggregated architecture that separates compute-intensive pr

This project provides a comprehensive technical guide and framework for engineering large-scale machine learning systems. It covers the full lifecycle of model development, focusing on the infrastructure and computational principles required to build, train, and serve generative AI models across distributed GPU clusters. The repository distinguishes itself by offering deep-dive tutorials and implementation strategies for complex system challenges. It emphasizes high-performance architectural primitives, such as collective communication orchestration, distributed tensor sharding, and static gr

Infinity is a distributed vector database and multimodal vector store designed to manage large-scale datasets for retrieval and similarity search. It serves as a backend for large language model applications and retrieval augmented generation pipelines by storing and retrieving dense vectors, sparse vectors, and full-text data. The system functions as a hybrid search engine, combining vector embeddings and full-text search with reranking algorithms to identify the most relevant documents. It supports multimodal data storage, allowing the maintenance of diverse data types including tensors, st

llama.cpp is a high-performance C++ inference engine and runtime for executing large language models locally across various hardware architectures. It provides the core components for local model execution, including a dedicated model quantizer for compressing weights into the GGUF format and a system for generating text embeddings for semantic search. The project distinguishes itself through specialized memory and execution optimizations, such as block-wise weight quantization to reduce memory footprints and memory-mapped model loading. It supports structured text generation by using formal

This project provides a comprehensive guide and set of scripts for deploying and configuring a production-ready Kubernetes cluster from scratch. It centers on establishing a functional environment by installing core management components, storage, and networking across multiple nodes. The implementation emphasizes high availability for the control plane, utilizing layer-4 load balancing and leader election for the API server, scheduler, and controller manager. It further ensures reliability through the deployment of a distributed key-value store for persistent runtime data. The project cover

LiteLLM is a unified gateway and proxy server designed to centralize access to over one hundred language model providers. It provides a standardized API interface that abstracts vendor-specific schemas, allowing developers to interact with diverse models through a single, consistent format. By acting as a central traffic management layer, it enables organizations to route, secure, and govern model interactions across multiple deployments. The platform distinguishes itself through its policy-driven architecture, which uses configuration-based routing to manage traffic distribution, load balanc

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

Polars is a high-performance columnar data processing library designed for efficient analytical workflows. It functions as a structured data library that organizes information into typed columns, utilizing the Apache Arrow memory format to enable zero-copy data sharing and cache-friendly, vectorized operations. The engine is built to handle large-scale tabular datasets, providing both local and distributed analytical runtimes that scale from single-machine environments to multi-node clusters. The project distinguishes itself through a sophisticated lazy query engine that constructs abstract e

This project is an AI-powered IDE extension and LLM coding assistant that provides a conversational interface for generating, refactoring, and debugging code. It functions as an AI agent framework and a Model Context Protocol client, connecting AI models to external data sources and tools to automate complex development tasks. The system is distinguished by its use of autonomous AI agents capable of multi-step task execution, including the ability to read files, modify code, and run terminal commands iteratively. It supports recursive agent orchestration through subagent delegation and employ