xdit-project / xDiT
xDiT: A Scalable Inference Engine for Diffusion Transformers (DiTs) with Massive Parallelism
☆1,846Updated last week
Alternatives and similar repositories for xDiT:
Users that are interested in xDiT are comparing it to the libraries listed below
- Quantized Attention that achieves speedups of 2.1-3.1x and 2.7-5.1x compared to FlashAttention2 and xformers, respectively, without lossi…☆1,329Updated this week
- [CVPR 2024 Highlight] DistriFusion: Distributed Parallel Inference for High-Resolution Diffusion Models☆674Updated 4 months ago
- SpargeAttention: A training-free sparse attention that can accelerate any model inference.☆453Updated this week
- Model Compression Toolbox for Large Language Models and Diffusion Models☆421Updated 3 weeks ago
- FastVideo is a lightweight framework for accelerating large video diffusion models.☆1,337Updated this week
- [ICLR2025 Spotlight] SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models☆1,463Updated this week
- 📖A curated list of Awesome Diffusion Inference Papers with codes: Sampling, Caching, Multi-GPUs, etc. 🎉🎉☆210Updated 3 weeks ago
- VideoSys: An easy and efficient system for video generation☆1,956Updated last month
- A highly optimized LLM inference acceleration engine for Llama and its variants.☆885Updated last week
- [CVPR 2025 Oral]Infinity ∞ : Scaling Bitwise AutoRegressive Modeling for High-Resolution Image Synthesis☆1,180Updated last month
- Vchitect-2.0: Parallel Transformer for Scaling Up Video Diffusion Models☆910Updated last month
- [CVPR'25]Tora: Trajectory-oriented Diffusion Transformer for Video Generation☆1,126Updated last month
- A fast communication-overlapping library for tensor/expert parallelism on GPUs.☆887Updated this week
- Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model☆687Updated this week
- Allegro is a powerful text-to-video model that generates high-quality videos up to 6 seconds at 15 FPS and 720p resolution from simple te…☆1,074Updated 2 months ago
- https://wavespeed.ai/ Context parallel attention that accelerates DiT model inference with dynamic caching☆243Updated 2 weeks ago
- [CVPR2024 Highlight] VBench - We Evaluate Video Generation☆914Updated this week
- Official repo of our paper "SDXS: Real-Time One-Step Latent Diffusion Models with Image Conditions"☆614Updated 10 months ago
- Memory-optimized training library for diffusion models☆1,048Updated last week
- [CVPR 2024] DeepCache: Accelerating Diffusion Models for Free☆886Updated 9 months ago
- [CVPR 2025 Highlight🔥] Identity-Preserving Text-to-Video Generation by Frequency Decomposition☆674Updated this week
- USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference☆473Updated last week
- Region-Aware Text-to-Image Generation via Hard Binding and Soft Refinement 🔥☆564Updated 3 months ago
- Liquid: Language Models are Scalable and Unified Multi-modal Generators☆517Updated last week
- Official implementation for "RIFLEx: A Free Lunch for Length Extrapolation in Video Diffusion Transformers"☆623Updated last month
- Ola: Pushing the Frontiers of Omni-Modal Language Model☆334Updated last month
- Align Anything: Training All-modality Model with Feedback☆3,386Updated this week
- https://wavespeed.ai/ Best inference performance optimization framework for HuggingFace Diffusers on NVIDIA GPUs.☆1,248Updated 3 weeks ago
- ☆106Updated this week
- Official Implementation of "Lumina-mGPT: Illuminate Flexible Photorealistic Text-to-Image Generation with Multimodal Generative Pretraini…☆584Updated 2 weeks ago