Stars
Agent framework and applications built upon Qwen>=3.0, featuring Function Calling, MCP, Code Interpreter, RAG, Chrome extension, etc.
verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework
OptiScaler bridges upscaling/frame gen across GPUs. Supports DLSS2+/XeSS/FSR2+ inputs, replaces native upscalers, enables FSR-FG/XeFG on non-FG titles. Supports Nukem mod for DLSSG-to-FSR3 FG.
Google Workspace CLI — one command-line tool for Drive, Gmail, Calendar, Sheets, Docs, Chat, Admin, and more. Dynamically built from Google Discovery Service. Includes AI agent skills.
Executive Memory for Coherent Long-Horizon Reasoning!
Use Claude Code as the foundation for coding infrastructure, allowing you to decide how to interact with the model while enjoying updates from Anthropic.
👨💻 Python cleanup script for macOS
Unofficial implementation for the paper "Mixture-of-Depths: Dynamically allocating compute in transformer-based language models"
Minimalistic large language model 3D-parallelism training
Efficient Triton Kernels for LLM Training
A one-of-a-kind resume builder that keeps your privacy in mind. Completely secure, customizable, portable, open-source and free forever. Try it out today!
User-friendly GUI wrapper for gallery-dl, spotDL and yt-dlp (Youtube Video Downloader)
[CVPR 2025 Highlight] The official CLIP training codebase of Inf-CL: "Breaking the Memory Barrier: Near Infinite Batch Size Scaling for Contrastive Loss". A super memory-efficiency CLIP training sc…
Multi-LoRA inference server that scales to 1000s of fine-tuned LLMs
Empowering RAG with a memory-based data interface for all-purpose applications!
A modern GUI client based on Tauri, designed to run in Windows, macOS and Linux for tailored proxy experience
Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud.
📄 Easily create your resume with Markdown on VSCode / Typora / Obsidian
Reduce the size of pretrained Hugging Face models via vocabulary trimming.
Freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.
Modeling, training, eval, and inference code for OLMo