#
Lists (4)
Starred repositories
official code of "MuDG: Taming Multi-modal Diffusion with Gaussian Splatting for Urban Scene Reconstruction"
The simplest, fastest repository for training/finetuning small-sized VLMs.
[CVPR 2025 Oral]Infinity ∞ : Scaling Bitwise AutoRegressive Modeling for High-Resolution Image Synthesis
[CVPR2024 Highlight]GLEE: General Object Foundation Model for Images and Videos at Scale
PyTorch implementation of MAR+DiffLoss https://arxiv.org/abs/2406.11838
Ring attention implementation with flash attention
A Distributed Attention Towards Linear Scalability for Ultra-Long Context, Heterogeneous Data Training
MAGI-1: Autoregressive Video Generation at Scale
Official PyTorch Implementation of "History-Guided Video Diffusion"
PyTorch implementation of FractalGen https://arxiv.org/abs/2502.17437
Pytorch implementation for the paper titled "SimpleAR: Pushing the Frontier of Autoregressive Visual Generation"
Code for: "Long-Context Autoregressive Video Modeling with Next-Frame Prediction"
Modern columnar data format for ML and LLMs implemented in Rust. Convert from parquet in 2 lines of code for 100x faster random access, vector index, and data versioning. Compatible with Pandas, Du…
ryderling / practicalAI
Forked from GokuMohandas/Made-With-MLA practical approach to learning machine learning.
Official implementations for paper: VACE: All-in-One Video Creation and Editing
Distributed Triton for Parallel Systems
Official inference repo for FLUX.1 models
A fast communication-overlapping library for tensor/expert parallelism on GPUs.
ByteCheckpoint: An Unified Checkpointing Library for LFMs
💥 Fast State-of-the-Art Tokenizers optimized for Research and Production
FireFlyer Record file format, writer and reader for DL training samples.
Freja71122 / GET3D
Forked from nv-tlabs/GET3DGET3D support multi nodes
HFAiLab / GET3D
Forked from Freja71122/GET3DGET3D with multi-nodes support
Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud.
The official implementation of "Neighboring Autoregressive Modeling for Efficient Visual Generation"