Open-source alternatives to Inference

Ktransformers is a comprehensive framework designed for the operation, fine-tuning, and serving of large language models. It functions as a heterogeneous inference engine and quantized execution runtime, enabling the deployment of massive models by distributing computational workloads across both CPU and GPU resources. This architecture allows users to bypass local memory constraints, making it possible to run and train models that exceed the capacity of a single device. The project distinguishes itself through specialized support for sparse architectures, particularly mixture-of-experts mode

LightLLM is a high-performance serving framework for deploying and executing large language models. It functions as a multi-GPU inference engine and server capable of handling dense architectures, mixture-of-experts designs, and multimodal models that process both text and images. The system is distinguished by its specialized support for Mixture-of-Experts models using expert parallelism and fused kernels. It implements structured text generation through deterministic state machines and pushdown automata to enforce precise output formats. To optimize throughput, the framework employs specula

OpenVINO is an AI inference engine and model serving platform designed to execute optimized deep learning models across CPUs, GPUs, and NPUs through a unified API. It includes a model optimization toolkit for converting, quantizing, and compressing models from various frameworks, alongside a specialized generative AI runtime for large language models. The project distinguishes itself through a plugin-based hardware acceleration layer that maps neural network operations to vendor-specific drivers. It features advanced execution mechanisms such as continuous batching, speculative decoding, and

This project is a framework for developing multimodal AI agents that function as programmable participants in real-time communication rooms. It enables the construction of agents that can see, hear, and speak by integrating speech-to-text, large language models, and text-to-speech pipelines to facilitate low-latency, natural conversations. The system is distinguished by its advanced orchestration of real-time media and conversational flow, including support for full-duplex speech, preemptive response generation, and sophisticated interruption management. It further differentiates itself throu

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

FastDeploy is a high-performance deployment framework for large language models, vision models, and multimodal models. It provides the infrastructure to launch model services that process combined image, video, and text inputs, exposing these capabilities through a standardized, OpenAI-compatible API for chat and text completions. The project distinguishes itself through advanced inference pipeline engineering and GPU optimization. It employs speculative decoding, tensor parallelism, and a disaggregated execution model that separates prefill and decode phases across different hardware resourc

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

FastChat is a training and serving platform for large language models that provides an integrated toolkit for fine-tuning, hosting, and benchmarking chatbots. It functions as an inference server capable of hosting multiple models and exposing them via a standardized API for chat applications. The platform distinguishes itself through a distributed model controller that manages worker nodes and routes requests across a hardware-agnostic inference layer supporting various accelerators. It includes a dedicated evaluation framework for assessing model quality using automated judges, multi-turn di

Triton Inference Server is a high-performance AI model inference server and multi-framework model runtime designed for deploying machine learning models across cloud, data center, and embedded edge infrastructure. It serves as an execution engine that allows for the concurrent running of models from various frameworks to optimize hardware utilization. The project features a dynamic batching inference engine that groups individual requests into larger batches to increase total processing throughput. It also provides a model ensemble pipeline, which enables the chaining of multiple models toget

This project is a PyTorch model serving framework designed to deploy and scale machine learning models in production via scalable network endpoints. It functions as a high-performance inference server, optimizer, and model lifecycle manager that handles model loading, request batching, and hardware acceleration. The system distinguishes itself through advanced orchestration and optimization capabilities, such as chaining multiple models into sequential workflows using execution graphs and employing dynamic batching to improve throughput and latency. It provides specialized support for generat

WebLLM is a library for executing large language models directly within web browsers. It provides a framework for building conversational artificial intelligence applications that perform inference locally, ensuring user data privacy by eliminating the need for external server dependencies. The project distinguishes itself by leveraging browser-native graphics APIs to perform intensive machine learning computations on the client side. It maintains application responsiveness by offloading heavy model tasks to background threads and ensures continuous operation through service workers that func

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

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

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,

KoboldCPP is a local large language model inference engine and GGUF model runner designed to execute quantized models on personal hardware. It functions as a multimodal AI server and API gateway, providing OpenAI-compatible endpoints that allow third-party clients to interact with locally hosted models. The project distinguishes itself as an AI storytelling backend, featuring dedicated tools for long-form narrative management through persistent memory, world lore tracking, and character state management. It further extends its capabilities as a multimodal server capable of processing text, im

Shimmy is a local large language model inference engine and server that loads and serves GGUF formatted weights. It is distributed as a single binary runtime written in Rust, providing a standalone environment for running models without external runtime dependencies. The project utilizes WebGPU for hardware acceleration, allowing model compute kernels to execute across diverse graphics hardware through a standardized interface. It features a local server that implements an OpenAI-compatible API layer, enabling applications to interface with local models via standardized REST endpoints. Memor

RouteLLM is a routing framework and traffic manager designed to direct prompts between high-capability and low-cost large language models. It functions as an API gateway that mimics the OpenAI specification to route requests across different model providers. The system optimizes operational costs by splitting traffic between model tiers based on predicted win rates and prompt complexity. It includes a calibration tool to analyze sample queries and determine the optimal cost-quality tradeoff for traffic distribution. The framework provides a tool for measuring the accuracy and cost efficiency

This project is a comprehensive platform for hosting and interacting with large language models directly on local hardware. It provides a web-based graphical interface that allows users to manage model loading, configure generation parameters, and execute text or chat interactions entirely offline. By running models locally, the software ensures complete data privacy and eliminates reliance on external cloud services for generative tasks. Beyond basic inference, the platform functions as a versatile workbench for generative AI development. It includes an integrated pipeline for fine-tuning mo

BAML is a prompt engineering framework and LLM client generator that defines AI prompts as type-safe functions. It serves as a structured data extraction tool and workflow orchestrator, transforming unstructured model responses into strongly typed objects using a custom schema language and alignment algorithms. The project distinguishes itself by using a compiler to generate language-specific boilerplate code for API communication and output parsing. It features a dedicated environment for designing complex prompt templates with conditional logic and reusable snippets, and employs genetic alg

LocalAI is a self-hosted inference server that enables the execution of machine learning models directly on local hardware. By providing a unified interface for text, image, and audio processing, it allows users to maintain full control over data privacy and infrastructure costs while eliminating dependencies on external network services. The platform functions as an API gateway that mimics standard cloud-based artificial intelligence interfaces, allowing existing applications to integrate local models as drop-in replacements. It utilizes a container-based architecture to package runtimes and

Lobe Chat is a self-hosted AI platform that provides a web-based interface for interacting with multiple large language models. It functions as an AI agent orchestrator, allowing for the design, scheduling, and management of autonomous agent teams to perform operational tasks. The platform features an extensible plugin framework and SDK to integrate external tools and custom function calls into workflows. It utilizes a provider-agnostic model layer to unify various AI APIs and includes a context-aware memory system to store structured user information for personalized interactions. The syste

Open WebUI is a self-hosted, web-based platform designed for interacting with local and remote artificial intelligence models. It functions as a unified interface and orchestration suite, enabling users to build, deploy, and manage specialized AI agents equipped with custom instructions, external tool access, and private knowledge bases. The platform distinguishes itself through a modular architecture that supports complex AI workflows. It features a plugin-based framework for custom logic and pipeline-based request processing, allowing developers to filter or transform data streams before th

Mem0 is an agent-agnostic memory layer designed to provide intelligent agents with long-term persistence and cross-session state management. By acting as a centralized service, it allows diverse AI agents to recall user preferences, past interactions, and historical context, ensuring continuity across multiple workflows and independent agent systems. The platform distinguishes itself through a multi-signal retrieval engine that combines semantic vectors, keyword matching, and entity-linked metadata to surface the most relevant information. It employs an adaptive memory engine that automatical

Ollama provides a framework for running and managing local machine learning models. It includes a command-line interface for model lifecycle management, such as creation, embedding generation, and configuration, alongside a stable API for programmatic interaction across multiple programming languages. The platform supports the import of models and adapters in various formats, including GGUF and Safetensors. Users can define custom model behaviors, prompt templates, and system messages through a configuration file format. It also offers tools for fine-tuning models with LoRA adapters and apply

Flowise is a low-code platform designed for building and deploying complex language model workflows through a visual, node-based interface. It functions as an orchestrator for autonomous multi-agent systems, allowing users to construct conversational pipelines by connecting language models, memory stores, and external tools on a drag-and-drop canvas. The platform distinguishes itself through its support for sophisticated agentic patterns, including supervisor-worker delegation and iterative reasoning strategies. Users can design directed acyclic graphs to manage conditional branching, state p

OpenLLM is a framework for deploying, managing, and scaling open-source large language models

Airllm is a framework designed to execute and fine-tune large language models on consumer-grade hardware. By employing layer-wise model decomposition and memory-efficient loading techniques, the engine enables the operation of massive models that would otherwise exceed available system or video memory. The project distinguishes itself through a suite of optimization strategies that balance memory footprint with performance. It utilizes block-wise weight quantization and asynchronous layer prefetching to reduce resource consumption and hide data transfer latency. Additionally, the framework su