Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.

极简风格的截屏翻译、复制翻译、词典翻译、离线翻译软件

vLLM plugin for attention-ffn disaggregation support

Run frontier MoE models on hardware you already own — pure C, zero deps, experts streamed from disk. Tiny engine, immense model. 🐦

DeepSpec: a full-stack codebase for training and evaluating speculative decoding algorithms

Collection of publicly available libraries

High-performance Rust benchmark client for vLLM serving endpoints.

网文/小说写作 skill 包，覆盖长篇与短篇网络小说的扫榜、拆文、写作、去AI味、封面图全流程 | An all-in-one skill pack for long- and short-form web fiction.

Flash OS images to SD cards & USB drives, safely and easily.

build llama inference compute from scrath, only using torch/numpy base ops

A unified library for building, evaluating, and storing speculative decoding algorithms for LLM inference in vLLM

Persist and reuse KV Cache to speedup your LLM.

A browser automation framework and ecosystem.

LeaderWorkerSet: An API for deploying a group of pods as a unit of replication

A machine learning-based video super resolution and frame interpolation framework. Est. Hack the Valley II, 2018.

Development repository for the Triton language and compiler

Common recipes to run vLLM

Production-Grade Container Scheduling and Management

One local control plane for every AI agent: route across models, fuse new capabilities, orchestrate tools, and stay fully in control.

一键将Markdown表格转换为Word兼容格式

Qwen3-TTS is an open-source series of TTS models developed by the Qwen team at Alibaba Cloud, supporting stable, expressive, and streaming speech generation, free-form voice design, and vivid voice…

Apache Spark - A unified analytics engine for large-scale data processing

Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models

GitHub Action for installing Kubectl

deep learning for image processing including classification and object-detection etc.

Trinity-RFT is a general-purpose, flexible and scalable framework designed for reinforcement fine-tuning (RFT) of large language models (LLM).