分布式模型推理框架

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

Petals is a decentralized framework and inference engine for running large language models across a peer-to-peer network. It enables the execution of models that exceed the memory of any single machine by splitting computations and model layers across a collaborative swarm of GPUs. The system functions as a collaborative compute network where participants share local GPU resources and host model weights. It supports distributed prompt-tuning to adapt massive models to specific tasks and allows for the establishment of private compute swarms to process sensitive data within restricted, trusted

Text Generation Inference is a production-ready engine designed for the deployment and serving of large language models. It functions as a containerized runtime environment that manages model execution, scales across distributed hardware, and provides high-performance inference capabilities for demanding production environments. The project distinguishes itself through advanced optimization techniques, including continuous batching to maximize hardware utilization and tensor parallelism to shard large models across multiple accelerator cards. It supports efficient inference through custom com

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

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

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

ipex-llm is an acceleration library and inference engine designed to optimize the execution and finetuning of large language models on Intel GPUs and NPUs. It provides a HuggingFace compatible model backend and a dedicated quantization toolkit for converting model weights into low-bit precision formats. The project facilitates distributed inference by splitting large model workloads across multiple accelerators using pipeline and tensor parallelism. It enables the deployment of models on Intel Arc, Flex, and Max GPUs to increase throughput and reduce latency. The library covers a broad range

ColossalAI is a distributed deep learning framework designed for training and deploying massive artificial intelligence models across clusters of hardware accelerators. It functions as a parallel computing engine that partitions model workloads and data across multiple processors to maximize memory efficiency and throughput. The platform distinguishes itself through a comprehensive suite of parallelization strategies, including multi-dimensional tensor parallelism and pipeline-based model parallelism, which segment neural network layers and stages across devices. To support large-scale genera

DeepSpeed is a high-performance library designed to scale deep learning model training and inference across massive clusters of GPUs and compute nodes. It provides a comprehensive suite of tools for distributed training, enabling the execution of models that exceed the memory capacity of single devices through advanced parameter partitioning, pipeline-based model parallelism, and memory-efficient state offloading. The framework distinguishes itself through specialized communication-efficient optimizers and hardware-aware acceleration techniques. By utilizing gradient compression, quantization

gpt-fast is a PyTorch transformer inference engine designed for low-latency text generation. It functions as a distributed GPU inference library, a quantized model runner, and a speculative decoding framework. The system utilizes a speculative decoding workflow where a small draft model predicts token sequences for verification by a larger model to accelerate generation. It supports quantized model execution to reduce memory footprint and implements tensor parallelism to split computations across multiple GPUs. The project includes a standardized evaluation harness to measure the accuracy an

vLLM is a high-throughput inference engine designed for the efficient serving and execution of large language models. It functions as a production-ready distributed model server, providing standard API protocols for online serving while also supporting offline batch processing. The system is built to maximize token generation speed and memory efficiency, enabling both large-scale cloud deployments and local execution on personal hardware. The project distinguishes itself through advanced memory management and request scheduling techniques, most notably its use of non-contiguous key-value cach

DeepSpeed is a distributed deep learning optimization library and framework designed for the training and inference of massive AI models. It serves as a model parallelism orchestrator and a toolkit for scaling large language models across multiple GPUs and compute nodes. The project distinguishes itself through 3D parallelism orchestration, which combines data, pipeline, and tensor parallelism. It utilizes ZeRO-based memory partitioning to eliminate redundant storage and employs CPU-offload memory management to move weights and optimizer states to system RAM. Additionally, it provides special

FasterTransformer is a high-performance inference optimization library and distributed runtime designed to accelerate the execution of transformer models. It provides a toolkit for reducing model precision and parallelizing execution across multiple GPUs to increase throughput and reduce latency for large language models. The framework utilizes a C++ backend with custom CUDA kernels to replace generic operations with optimized GPU instructions. It implements tensor and pipeline parallelism to shard model weights and distribute compute operations across multiple devices. The system includes c

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

vllm-omni is a high-throughput serving engine and distributed inference framework designed for omni-modal models. It serves as a multi-modal model API server capable of generating text, image, video, and audio data, providing a standardized interface for remote client access. The system features a non-autoregressive generation engine for parallel media production and a robot policy inference server that acts as a real-time communication bridge to robotic hardware using specialized protocols. It supports hybrid execution models that combine sequential token generation with parallelized media g

ds4 is a local inference engine for DeepSeek models that includes a distributed runtime for splitting transformer layers across networked computers. It functions as a reasoning controller with a local weight streamer and an API server that streams chat completions via industry standard endpoints. The system employs a memory management model that loads model experts from disk on demand to execute models that exceed available system RAM. It provides controls for reasoning effort and model behavior steering, allowing the modification of response characteristics through activation directions. Th

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

TensorFlow is a comprehensive machine learning framework designed for the construction, training, and deployment of complex mathematical models. It utilizes a graph-based execution model that represents operations as directed acyclic graphs, enabling automatic differentiation and efficient parallel processing. The system provides high-level interfaces for defining neural network architectures, alongside a robust engine for managing multidimensional array structures and tensor mathematics. The framework distinguishes itself through a scalable distributed runtime that orchestrates workloads acr

Intel XPU LLM Acceleration Library is a toolkit designed to accelerate large language model inference and finetuning on Intel CPUs, GPUs, and NPUs. It provides a distributed inference engine for scaling models across multiple accelerators, a multimodal model runtime for vision and speech tasks, and a low-bit model quantization tool for converting weights into INT4, FP8, and GGUF formats. The project features a parameter-efficient finetuning framework that enables model adaptation using QLoRA and DPO on Intel hardware. It distinguishes itself by providing specialized optimizations for Intel XP

Transformers is a comprehensive library for machine learning that provides a unified interface for training, fine-tuning, and deploying transformer-based models. It supports a wide range of tasks, including text classification, language modeling, question answering, and sequence-to-sequence translation, while offering specialized architectures for both text and vision processing. The framework includes tools for managing the entire model lifecycle, from data preprocessing and tokenization to distributed training and inference. The library features extensive support for model optimization and

Llama is a large language model runtime and inference engine designed to load and execute autoregressive transformer models. It enables the generation of natural language text completions from prompts using pretrained weights. The system features multi-GPU model parallelism, which distributes model weights and workloads across multiple graphics processors to support larger parameter counts. It also incorporates a content safety filter that uses classifiers to intercept and block unsafe inputs or outputs during the inference process. The project covers broad capabilities in distributed model

Documentation | Slack

Qwen is a comprehensive framework for large language model development, serving, and deployment. It provides a complete ecosystem for transformer-based sequence modeling, offering base models alongside specialized tools for instruction-tuned alignment, fine-tuning, and long-context inference. The project is designed to support both research and production environments, enabling users to train, optimize, and host generative models locally or across distributed hardware. The framework distinguishes itself through its focus on high-performance serving and extensibility. It features a high-perfor

LocalAI is a local generative AI platform and inference engine designed to host large language, vision, and audio models on private hardware. It functions as an API compatible gateway that mimics proprietary service endpoints, allowing existing third-party software to integrate with a self-hosted backend. The platform distinguishes itself as a distributed AI model orchestrator, capable of scaling inference across machine clusters using VRAM-aware routing and hardware coordination. It provides a unified interface for diverse open-source backends and supports self-hosted RAG infrastructure thro