Projects sharing features with Openchat

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

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

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

ChatGLM3 is a comprehensive framework for deploying, fine-tuning, and serving large language models. It functions as a high-performance inference engine designed to support conversational AI, enabling developers to build interactive agents capable of multi-turn dialogue, autonomous code execution, and structured tool invocation. The project distinguishes itself through its focus on hardware-agnostic deployment and resource optimization. It supports distributed model parallelism across multiple graphics cards, paged key-value caching for concurrent request processing, and weight quantization t

WeClone is an end-to-end framework designed for the creation, training, and deployment of personalized conversational AI digital twins. By fine-tuning large language models on individual chat history, the platform enables the replication of unique communication styles, speech patterns, and conversational habits. The system manages the entire lifecycle of these digital avatars, from initial data preparation to final integration into messaging platforms for real-time interaction. The platform distinguishes itself through a comprehensive suite of data processing utilities that prepare raw messag

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

This project is a technical curriculum and development guide focused on large language model prompt engineering, fine-tuning, and the creation of retrieval augmented generation applications. It serves as a comprehensive resource for developers to master crafting precise instructions and textual patterns to improve the quality and predictability of model outputs. The material covers the end-to-end workflow of adapting open-source models to specific datasets and integrating language models with vector databases to generate responses based on private information. It also provides a systematic ap

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

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

This project is an educational curriculum and set of technical guides for building production-ready large language model and retrieval augmented generation systems. It provides instructional materials and hands-on lessons focused on model specialization, LLMOps, and the implementation of vector databases. The course covers the development of retrieval augmented generation systems, including tutorials on creating data pipelines that crawl, chunk, and embed content into vector stores. It includes training guides for the deployment, monitoring, and maintenance of language models in production en

InternLM is a large language model and a comprehensive suite of weights designed for text generation and complex reasoning. It functions as an inference engine for serving responses, a fine-tuning framework for adjusting model weights, and a platform for building autonomous AI agents. The system is capable of processing long-context input sequences up to one million tokens for document analysis. It employs chain-of-thought reasoning to solve knowledge-intensive tasks by generating intermediate logic steps before producing a final answer. The project covers model weight optimization through s

KServe is a Kubernetes-native platform for deploying and serving machine learning models as scalable inference services. It supports both generative AI models, including large language models, and traditional predictive models from frameworks such as TensorFlow, PyTorch, Scikit-Learn, XGBoost, and ONNX. The platform manages the full lifecycle of model deployments, including revision tracking, canary rollouts, A/B testing, and automatic rollbacks, and provides serverless scale-to-zero capabilities for cost-efficient resource management. KServe distinguishes itself through a standardized infere

This project is a comprehensive toolkit designed for the full lifecycle management of large language and multimodal models. It functions as a unified orchestrator that handles the entire development process, ranging from dataset preparation and supervised fine-tuning to advanced reinforcement learning alignment and production-ready inference deployment. The platform distinguishes itself through a specialized reinforcement learning library that supports complex optimization algorithms, including group relative policy optimization and leave-one-out techniques, to improve model instruction-follo

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

Qwen-7B is a pretrained causal language model designed for natural language generation, text processing, and complex reasoning tasks. It is available as an instruction-tuned model optimized for conversational interactions and a tool-use model capable of executing function calls and interacting with external APIs. The project provides a quantized version of the model to reduce GPU memory usage and supports the development of autonomous agents that can execute code and perform functions to complete complex goals. The system covers a wide range of capabilities including model fine-tuning throug

This project is a language model finetuning framework designed to adapt large language models to specific datasets using supervised fine-tuning and low-rank adaptation. It serves as a distributed training manager that coordinates workloads and synchronizes gradients across multiple processing units to scale performance. The framework includes a specialized toolkit for low-rank adaptation to update a subset of model weights, reducing memory and hardware requirements. It provides capabilities for instruction fine-tuning, domain adaptation, and the optimization of function calling to improve how

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

Gemma is a family of open-weights large language models based on a decoder-only transformer architecture. These models are designed for text generation and multi-modal conversations, capable of processing and generating responses based on both textual and visual input sequences. The project provides a fine-tunable AI model that supports weight adjustment and low-rank adaptation to specialize performance for particular tasks. It includes support for quantized weights to reduce memory usage and increase inference speed on limited hardware. The capability surface covers multi-modal AI integrati

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

This project is a fine-tuning framework and training pipeline designed to optimize and adapt large language and vision models. It provides a specialized toolkit for parameter-efficient tuning and supervised learning, serving as both a trainer for multimodal models and a deployment tool for serving fine-tuned models via high-performance inference engines. The framework focuses on reducing memory and compute requirements by updating a small subset of model parameters. It supports a wide range of adaptation strategies, including vision-language model training to align text, image, video, and aud

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.

This project is a comprehensive framework and toolkit for developing, optimizing, and deploying transformer-based models across multimodal, document intelligence, and natural language processing tasks. It provides a unified neural architecture that processes text, vision, audio, and document layout data through a shared set of weights, enabling researchers and developers to build foundational models that align cross-modal representations. The platform distinguishes itself through advanced training and inference strategies designed for large-scale deep learning. It incorporates specialized mec

Deep Java Library is a Java deep learning framework and JVM model inference engine. It provides a high-level API for building and deploying deep learning models within the Java ecosystem, acting as a cross-platform runtime for executing models across CPUs, GPUs, and mobile devices. The library is engine-agnostic, allowing users to switch between different deep learning engines such as PyTorch, TensorFlow, and MXNet while maintaining a single unified API. This enables the deployment of the same model across different backends without changing the application code. The framework supports the f

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

Smile is a comprehensive JVM machine learning library and statistical computing toolkit. It provides a suite of algorithms for classification, regression, and clustering, implemented natively for Java, Scala, and Kotlin. The project also functions as a deep learning framework, a natural language processing library, and an inference engine for large language models. The library distinguishes itself through GPU acceleration via LibTorch bindings and support for the ONNX model interchange format. It includes specialized capabilities for large language model inference, featuring Byte-Pair Encodin

UltraChat is a collection of large-scale conversational datasets and instruction-tuning data designed for training and evaluating generative AI models. It provides structured JSON data consisting of complex, multi-round dialogue sequences intended to refine the performance of large language models in chat tasks. The project focuses on improving reasoning and response quality through a diverse set of interactions across multiple sectors. These datasets are used for supervised fine-tuning and instruction tuning workflows to improve how models follow complex directions and maintain context acros

Metaseq is a transformer sequence modeling toolkit designed for training, fine-tuning, and deploying sequence-to-sequence models using open pre-trained weights. It provides a comprehensive framework for large language model training, including dedicated tools for sequence dataset processing and a standalone inference server for generating text via API requests. The project features specialized utilities for model quantization to reduce parameter precision to eight bits, which lowers memory usage and increases inference speed. It also includes a checkpoint conversion pipeline to transform mode