LLM optimization framework

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

BitNet is a quantized inference engine designed to execute highly compressed language models by performing arithmetic on low-precision, bit-level weight data. It functions as a model optimization toolkit and a high-performance kernel library, enabling the execution of large language models on consumer hardware by reducing memory footprints and increasing processing speeds. The project distinguishes itself through hardware-specific kernel optimizations that leverage native processor instructions to accelerate matrix multiplication. By utilizing packed integer arithmetic and memory-aligned weig

PaddleNLP is a development library and toolkit for training, fine-tuning, and deploying large and small language models using the PaddlePaddle framework. It provides a comprehensive suite for the entire natural language processing lifecycle, from model development to high-performance inference. The project features a standardized model zoo for loading and managing pre-trained models and tokenizers through a unified interface. It distinguishes itself with a specialized model compression framework that reduces memory footprints via weight precision conversion and lossless size optimization, alo

Neural Compressor is a deep learning model compression toolkit and AI inference acceleration engine. It functions as an automated model quantization tool and hardware-aware model compiler designed to reduce the memory footprint of neural networks and decrease execution latency. The project provides specialized frameworks for optimizing large language models, utilizing weight-only quantization and hardware-specific kernels to improve the operational efficiency of generative AI workloads. It maps neural network operators to specialized CPU and GPU vector instructions to accelerate model executi

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

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

PowerInfer is an inference engine and serving framework designed to run large language models on local hardware. It combines a hybrid CPU-GPU offloader, a quantization tool, and a sparse model optimizer to enable the execution of high-parameter models on consumer-grade devices. The system distinguishes itself through neuron-activation-based offloading, using a predictor model to preload frequent neurons into VRAM while keeping rare neurons in system memory. This hybrid execution model balances workloads between the GPU and CPU based on input patterns to optimize memory access and increase tok

This project is a comprehensive framework for the training, fine-tuning, and deployment of large language models. It functions as a distributed deep learning platform that enables users to scale model workflows across multiple hardware nodes while providing tools for model evaluation and performance benchmarking. The platform distinguishes itself by offering specialized utilities for model compression and weight transformation, allowing users to reduce memory footprints and latency through quantization and pruning. It supports the adaptation of large models for consumer-grade hardware, facili

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

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

FlexGen is an inference engine for large language models designed for high-throughput execution on single or multiple GPUs. It functions as a framework for managing model execution through a combination of memory offloading, weight compression, and pipeline orchestration. The system enables the execution of models that exceed available GPU memory by moving tensors and caches between GPU memory, system RAM, and disk storage. It utilizes 4-bit weight quantization to reduce the memory footprint of model parameters, allowing for increased batch processing capacity. The project covers distributed

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

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

This project is a comprehensive framework for the entire lifecycle of transformer-based language models, supporting everything from foundational pretraining to specialized deployment. It provides a modular toolkit for defining neural network architectures, managing data preparation pipelines, and executing training routines across various scales. The framework is designed to handle the full model development process, including supervised fine-tuning, behavioral alignment, and the integration of agentic capabilities. What distinguishes this framework is its focus on efficient training and adva

LMCache is a distributed key-value cache manager and tiering system designed to accelerate large language model inference. It functions as a tiered storage layer that offloads tensors from GPU memory to CPU RAM, local disks, or remote object stores, enabling the reuse of cached prefixes across different inference sessions and serving engines. The system differentiates itself through a disaggregated prefill-decode model, which separates prompt processing from token generation by transferring caches between distributed compute nodes. It utilizes peer-to-peer orchestration to share and retrieve

Swift is a toolkit for the full-parameter and parameter-efficient fine-tuning of large language and multimodal models. It functions as a multimodal model trainer for text, image, video, and audio data, and includes specialized tools for model compression and reinforcement learning from human feedback. The framework provides an alignment toolkit for optimizing model behavior using preference learning algorithms and reinforcement learning. It integrates parameter-efficient fine-tuning methods to adapt models with minimal memory and compute requirements, alongside utilities for reducing hardware

Torchtune is a PyTorch-native library for fine-tuning, aligning, and quantizing large language models. It provides a configurable training pipeline orchestrated through YAML recipes, with CLI overrides and component swapping, distributed training via FSDP2, memory optimizations, and parameter-efficient fine-tuning methods like LoRA, DoRA, and QLoRA. The library distinguishes itself through its YAML-driven configuration system that defines all training parameters and instantiates components from config files, with full CLI override capability for any field or component at launch time. It suppo

MLC LLM is a machine learning compiler and inference engine designed to execute large language models locally across diverse hardware platforms, including desktop, mobile, and web environments. By utilizing machine learning compilation, the project transforms high-level model definitions into specialized, hardware-specific binary libraries. This process optimizes model weights and generates compute kernels tailored to the unique memory and processing characteristics of target graphics and mobile hardware. The engine distinguishes itself by providing a unified runtime abstraction that enables

Nano-vllm is a high-performance inference engine designed for executing large language models locally. It functions as a specialized runtime that prioritizes accelerated token generation and efficient hardware utilization for text generation tasks. The project distinguishes itself through a comprehensive suite of optimization techniques, including a graph compilation engine that transforms neural network operations into pre-compiled execution plans. It also incorporates a tensor parallelism framework to distribute model weights across multiple hardware accelerators, effectively reducing memor

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

TensorRT-LLM is a platform and toolkit designed for compiling, optimizing, and serving transformer-based models on accelerated hardware. It functions as a framework that transforms machine learning models into efficient execution graphs, providing an engine to refine these models for specific hardware to maximize throughput and minimize latency during text generation. The project distinguishes itself through advanced execution strategies that manage the entire inference pipeline. It utilizes kernel-level fusion and static graph execution to optimize mathematical operations and computational f

🚀 Accelerate inference and training of 🤗 Transformers, Diffusers, TIMM and Sentence Transformers with easy to use hardware optimization tools

Model-Optimizer is a deep learning toolkit and framework dedicated to compressing, pruning, quantizing, and optimizing neural network architectures. It provides methodologies covering weight quantization, model distillation, and speculative decoding for efficient text generation, alongside automated neural architecture search for discovering optimal network structures. The library implements post-training quantization pipelines that convert high-precision neural network weights into lower-bit formats using calibration data. Additional optimization techniques include teacher-student knowledge

Oumi is a comprehensive large language model development platform designed for synthesizing data, fine-tuning models, and running performance evaluations. It serves as a unified environment for the entire model lifecycle, encompassing a training and fine-tuning suite, an evaluation framework, and tools for synthetic data generation and model distillation. The platform is distinguished by its iterative, failure-driven synthesis approach, which analyzes model weaknesses during evaluation to generate targeted training data. It utilizes an LLM-based judge framework to programmatically score respo

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,

This library provides a framework for parameter-efficient fine-tuning, enabling the adaptation of large pretrained models by training only a small subset of parameters. It functions as a distributed model training system and optimization toolkit, designed to reduce the computational and memory requirements typically associated with full model fine-tuning. The project distinguishes itself through a suite of methods for modular adapter composition, including low-rank matrix decomposition and activation-based scaling. It supports the integration of multiple task-specific adapter modules, allowin

Torchtune is a PyTorch-native library for fine-tuning, aligning, and quantizing large language models. It provides a config-driven system for instantiating components, orchestrating distributed training, and managing parameter-efficient fine-tuning with quantization support, all through YAML-based configurations and command-line overrides. The library distinguishes itself through its comprehensive post-training workflow orchestration, combining supervised fine-tuning, preference optimization (DPO, PPO, GRPO), knowledge distillation, and quantization-aware training in a single configurable pip

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

xtuner is a comprehensive training engine for large language models, offering a toolkit for pre-training, supervised fine-tuning, and the optimization of vision-language multimodal models. It serves as a distributed training accelerator and a specialized framework for scaling Mixture-of-Experts models and aligning model behavior through reinforcement learning from human feedback. The project distinguishes itself through advanced memory and compute optimizations, such as sequence parallelism for ultra-long context windows and interleaved pipeline parallelism to reduce GPU idle time. It provide

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

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

This project is a cross-platform machine learning inference engine designed to execute pre-trained models across diverse operating systems and hardware environments. It functions as a standardized execution framework that manages the entire lifecycle of model inference, from loading and graph optimization to hardware-accelerated execution and generative sequence management. The runtime distinguishes itself through a highly modular architecture that decouples model logic from hardware-specific kernels. By utilizing an execution provider abstraction, it enables developers to offload computation

LlamaFactory is a unified framework for fine-tuning and adapting large language models. It provides a comprehensive platform that standardizes training workflows across diverse machine learning architectures, allowing users to execute both full-tuning and parameter-efficient methods through a single interface. The project distinguishes itself by offering a low-code visual dashboard that enables users to configure experiments and monitor performance metrics in real time without writing extensive custom scripts. It also features a configuration-driven orchestration system that decouples experim

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

This project is a multimodal model trainer and machine learning fine-tuning tool that provides a containerized workflow for adapting pre-trained models to specific tasks. It features a no-code web interface and a dashboard for training large language models and other machine learning datasets without writing code. The system distinguishes itself by integrating a no-code interface with remote GPU orchestration, allowing users to deploy containerized training environments on cloud infrastructure or local hardware. It includes a dedicated integrator for uploading trained model weights and config

Nanochat is a lightweight execution environment designed for training and running language models on standard consumer hardware. It functions as both a neural network training framework and an inference engine, enabling users to perform backpropagation-based training and model execution directly on general-purpose processors without the need for dedicated graphics hardware. The project distinguishes itself through a suite of optimization tools that prioritize efficiency on local machines. By utilizing memory-mapped weight loading and CPU-optimized vector math, it maximizes throughput for inte

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

AutoGPTQ is a model compression framework designed to reduce the memory footprint and increase the inference speed of large language models. It utilizes the GPTQ algorithm to compress model weights, allowing these models to run on hardware with limited VRAM. The toolkit provides an architecture quantization pipeline that supports the integration of custom model classes for various neural network architectures. It includes a mixed-precision inference engine with optimized kernels to accelerate matrix multiplication during deployment. The framework covers the full weight-compression workflow,

Unsloth is a high-performance training and inference platform designed to optimize the lifecycle of large language and multimodal models. It provides a comprehensive engine for fine-tuning, executing, and managing models locally, with a focus on reducing memory consumption and increasing compute speed on consumer-grade hardware. The platform distinguishes itself through hand-optimized kernels and automated computational graph techniques that maximize hardware throughput. It supports advanced training methodologies, including reinforcement learning for reasoning and efficient adapter-based fin

Llama is a computational framework and runtime environment designed for executing transformer-based neural networks locally. It functions as a generative AI inference engine, enabling the processing of input sequences through pre-trained model weights to produce text completions and structured data outputs directly on your own hardware. The system distinguishes itself through specialized memory and computation management techniques, including memory-mapped weight loading and quantization-aware inference, which allow for efficient execution on standard consumer hardware. It utilizes a stateles

⚡ Build your chatbot within minutes on your favorite device; offer SOTA compression techniques for LLMs; run LLMs efficiently on Intel Platforms⚡

S-LoRA is a serving engine and execution framework built for hosting massive collections of task-specific language model adapters simultaneously on shared graphics hardware. It functions as a multi-tenant platform capable of managing thousands of concurrent fine-tuned adapters while maintaining high throughput and low overhead. The platform relies on dynamic adapter weight scheduling to route incoming requests and swap weights on demand, paired with a shared dynamic memory pool that allocates video memory to handle varying adapter ranks and sequence lengths without fragmentation. Custom heter

Torch-Pruning is a deep learning model pruning tool and neural network optimization toolkit designed for PyTorch. The library analyzes neural network graphs to remove redundant parameters and channels, reducing model size and computational costs. The framework traces computational graphs dynamically using sample inputs to map relational dependencies and identify coupled layers that require simultaneous pruning. It evaluates and ranks layer parameters across the entire network using global importance ranking and applies structural constraints to optimize overall outcomes. Additional capabili