xdit-project / xDiT
xDiT: A Scalable Inference Engine for Diffusion Transformers (DiTs) with Massive Parallelism
☆1,663Updated 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…☆1,185Updated this week
- [CVPR 2024 Highlight] DistriFusion: Distributed Parallel Inference for High-Resolution Diffusion Models☆670Updated 3 months ago
- VideoSys: An easy and efficient system for video generation☆1,944Updated 2 weeks ago
- [CVPR 2024] DeepCache: Accelerating Diffusion Models for Free☆871Updated 9 months ago
- Infinity ∞ : Scaling Bitwise AutoRegressive Modeling for High-Resolution Image Synthesis☆1,031Updated last month
- Model Compression Toolbox for Large Language Models and Diffusion Models☆394Updated last month
- https://wavespeed.ai/ Best inference performance optimization framework for HuggingFace Diffusers on NVIDIA GPUs.☆1,244Updated this week
- 📖A curated list of Awesome Diffusion Inference Papers with codes: Sampling, Caching, Multi-GPUs, etc. 🎉🎉☆199Updated this week
- [CVPR'25]Tora: Trajectory-oriented Diffusion Transformer for Video Generation☆1,105Updated 3 weeks ago
- A highly optimized LLM inference acceleration engine for Llama and its variants.☆881Updated 2 weeks ago
- [ICLR2025 Spotlight] SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models☆1,033Updated this week
- FastVideo is a lightweight framework for accelerating large video diffusion models.☆1,264Updated this week
- Context parallel attention that accelerates DiT model inference with dynamic caching☆228Updated 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…☆1,063Updated last month
- Memory-optimized training library for diffusion models☆995Updated this week
- SpargeAttention: A training-free sparse attention that can accelerate any model inference.☆328Updated 2 weeks ago
- Next-Token Prediction is All You Need☆2,042Updated last week
- [CVPR 2025🔥] Identity-Preserving Text-to-Video Generation by Frequency Decomposition☆647Updated last month
- Vchitect-2.0: Parallel Transformer for Scaling Up Video Diffusion Models☆908Updated last week
- Official repo of our paper "SDXS: Real-Time One-Step Latent Diffusion Models with Image Conditions"☆610Updated 10 months ago
- Region-Aware Text-to-Image Generation via Hard Binding and Soft Refinement 🔥☆555Updated 2 months ago
- [CVPR2024 Highlight] VBench - We Evaluate Video Generation☆848Updated last week
- USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference☆458Updated last week
- A fast communication-overlapping library for tensor/expert parallelism on GPUs.☆787Updated last week
- [ICLR 2025] Repository for Show-o, One Single Transformer to Unify Multimodal Understanding and Generation.☆1,284Updated this week
- Muon is Scalable for LLM Training☆974Updated last month
- ☆822Updated 3 months ago
- Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model☆571Updated last week
- Ring attention implementation with flash attention☆714Updated last month
- Align Anything: Training All-modality Model with Feedback☆3,063Updated this week