The official code of HeadArtist: Text-conditioned 3D Head Generation with Self Score Distillation

Talk to any LLM with hands-free voice interaction, voice interruption, and Live2D taking face running locally across platforms

Code base for Fast3R: Towards 3D Reconstruction of 1000+ Images in One Forward Pass

implementation of dualformer

Towards Economical Inference: Enabling DeepSeek's Multi-Head Latent Attention in Any Transformer-based LLMs

OpenMMLab Multimodal Advanced, Generative, and Intelligent Creation Toolbox. Unlock the magic 🪄: Generative-AI (AIGC), easy-to-use APIs, awsome model zoo, diffusion models, for text-to-image genera…

从无名小卒到大模型（LLM）大英雄~ 欢迎关注后续！！！

Transformers-compatible library for applying various compression algorithms to LLMs for optimized deployment with vLLM

Official repository for VisionZip (CVPR 2025)

A Unified Tokenizer for Visual Generation and Understanding

EasyR1: An Efficient, Scalable, Multi-Modality RL Training Framework based on veRL

A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)

Codes of MVSFormer++: Revealing the Devil in Transformer’s Details for Multi-View Stereo (ICLR2024)

The repo for "Distill Any Depth: Distillation Creates a Stronger Monocular Depth Estimator"

USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference

xDiT: A Scalable Inference Engine for Diffusion Transformers (DiTs) with Massive Parallelism

[CVPR 2024 - Highlight] FAR: Flexible, Accurate and Robust 6DoF Relative Camera Pose Estimation

NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This repository contains the open source components of TensorRT.

Optmized Fused-SSIM

A high-performance distributed file system designed to address the challenges of AI training and inference workloads.

Virtual whiteboard for sketching hand-drawn like diagrams

TransMLA: Multi-Head Latent Attention Is All You Need

official repo of paper for "CamI2V: Camera-Controlled Image-to-Video Diffusion Model"

Open Source Deep Research Alternative to Reason and Search on Private Data. Written in Python.

[CVPR 2025] Official PyTorch implementation of Rectified Diffusion Guidance for Conditional Generation

Analyze computation-communication overlap in V3/R1.

A library for advanced large language model reasoning

A curated collection of resources, tutorials, and best practices for learning and mastering NVIDIA CUTLASS