Open-source alternatives to Lingbot Map

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

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

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

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

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

Open Design is an AI design orchestration platform and LLM agent workspace designed for generating prototypes, presentations, and motion graphics. It functions as a local-first environment that integrates various command-line AI agents and coding tools into a unified design workflow, allowing users to migrate design specifications into brand-compliant source code. The project is distinguished by its ability to enforce visual consistency through a design system manager that defines brand contracts and tokens using Markdown. It features a specialized motion graphics generator that converts HTML

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

FlashInfer is a library of high-performance GPU kernels purpose-built for accelerating large language model inference. It provides optimized implementations for attention operations (including flash attention, page attention, multi-head latent attention, and cascade attention) using paged key-value caches, fused kernel composition, and just-in-time compilation. The library also includes specialized kernels for mixture-of-experts layers, block-scaled low-precision quantization (FP8, FP4), and distributed collective communication. What distinguishes FlashInfer is its fused all-reduce communicat

Hyperframes is an HTML-to-video rendering engine and composition tool that transforms web layouts and CSS into encoded video files. It functions as a headless browser video pipeline and a distributed video rendering framework, allowing users to create seekable animations and programmatic motion designs using HTML, CSS, and JavaScript. The project differentiates itself as an AI agent video orchestrator, enabling the automation of video scripts and compositions through natural language prompts. It supports distributed video encoding by splitting rendering tasks across multiple serverless functi

InstantMesh is a neural 3D reconstruction tool and single-image 3D mesh generator. It utilizes a sparse-view large reconstruction model to convert a single two-dimensional image into a three-dimensional object mesh. The system functions as a textured 3D mesh exporter, saving generated objects with either vertex colors or full texture maps for use in external rendering software. The framework covers a range of capabilities including feed-forward geometry inference, single-image depth estimation, and neural radiance fields. It also supports differentiable mesh rendering and workflows for spars

Discoart is a diffusion model orchestration framework and distributed GPU generation engine designed to automate and scale image generation workflows across hardware clusters. It functions as a generative AI model API, providing HTTP and gRPC endpoints to trigger and retrieve images from diffusion models as a network service. The system distinguishes itself through a comprehensive task management layer that includes timeline-based prompt and parameter scheduling. It manages the generative art lifecycle by supporting state-based session serialization for recovery, YAML-based configuration mana

og-image is an Open Graph image generator and HTML-to-image API designed to create custom, data-driven preview images for sharing links on platforms such as Twitter, Facebook, and Slack. It functions as a dynamic social card service that converts HTML and CSS layouts into static image files. The service automates the production of social media preview images and Open Graph metadata assets, allowing for the creation of personalized sharing cards based on page content or user data without manual graphic design. The system utilizes a layout engine to translate HTML and CSS into SVG strings, whi

Puppeteer is a browser automation library that provides a programmatic interface for controlling web browsers to execute tasks, simulate user interactions, and perform end-to-end testing. It functions as a headless browser controller, managing browser lifecycles, isolated session contexts, and remote connections to facilitate stable, automated web-based workflows. The library distinguishes itself through its deep integration with the Chrome DevTools Protocol, utilizing a bidirectional message bus to execute commands and receive real-time event notifications. It supports advanced automation pa