Starred repositories
VeOmni: Scaling Any Modality Model Training with Model-Centric Distributed Recipe Zoo
An open source, self-hosted implementation of the Tailscale control server
[CVPR 2025] Open-source, End-to-end, Vision-Language-Action model for GUI Agent & Computer Use.
PyTorch Extension Library of Optimized Autograd Sparse Matrix Operations
FlashMLA: Efficient Multi-head Latent Attention Kernels
Convert PDF to markdown + JSON quickly with high accuracy
Open-source evaluation toolkit of large multi-modality models (LMMs), support 220+ LMMs, 80+ benchmarks
Build SVM from scratch using only Python and some helper libraries: pandas, numpy,..
Survey Paper List - Efficient LLM and Foundation Models
Change the dates of several git commits with a single command
Efficient Multimodal Large Language Models: A Survey
[NeurIPS 2024 Best Paper Award][GPT beats diffusion🔥] [scaling laws in visual generation📈] Official impl. of "Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction". A…
A curated list for Efficient Large Language Models
This repository contains demos I made with the Transformers library by HuggingFace.
Official inference repo for FLUX.1 models
SwiftBrush: One-Step Text-to-Image Diffusion Model with Variational Score Distillation (CVPR 2024)
A high-throughput and memory-efficient inference and serving engine for LLMs
Code for studying the super weight in LLM
This repo provides a working re-implementation of Latent Adversarial Diffusion Distillation by AMD
Efficient Triton Kernels for LLM Training
The all-in-one Desktop & Docker AI application with built-in RAG, AI agents, No-code agent builder, MCP compatibility, and more.
Official inference framework for 1-bit LLMs
Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesis
[EMNLP Findings 2024] MobileQuant: Mobile-friendly Quantization for On-device Language Models
Fast and memory-efficient exact attention
GitPython is a python library used to interact with Git repositories.