thu-ml / SageAttentionLinks
Quantized Attention achieves speedup of 2-5x and 3-11x compared to FlashAttention and xformers, without lossing end-to-end metrics across language, image, and video models.
☆1,766Updated last week
Alternatives and similar repositories for SageAttention
Users that are interested in SageAttention are comparing it to the libraries listed below
Sorting:
- xDiT: A Scalable Inference Engine for Diffusion Transformers (DiTs) with Massive Parallelism☆2,044Updated this week
- SpargeAttention: A training-free sparse attention that can accelerate any model inference.☆620Updated last week
- Model Compression Toolbox for Large Language Models and Diffusion Models☆501Updated 2 months ago
- [ICLR2025 Spotlight] SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models☆2,059Updated this week
- Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model☆889Updated 2 weeks ago
- FastVideo is a unified framework for accelerated video generation.☆1,552Updated this week
- https://wavespeed.ai/ Context parallel attention that accelerates DiT model inference with dynamic caching☆304Updated last month
- 📚A curated list of Awesome Diffusion Inference Papers with Codes: Sampling, Caching, Quantization, Parallelism, etc.☆283Updated this week
- [CVPR 2024 Highlight] DistriFusion: Distributed Parallel Inference for High-Resolution Diffusion Models☆686Updated 6 months ago
- [CVPR 2024] DeepCache: Accelerating Diffusion Models for Free☆897Updated 11 months ago
- [ICML2025] Sparse VideoGen: Accelerating Video Diffusion Transformers with Spatial-Temporal Sparsity☆344Updated 2 weeks ago
- End-to-end recipes for optimizing diffusion models with torchao and diffusers (inference and FP8 training).☆360Updated 3 weeks ago
- Enhance-A-Video: Better Generated Video for Free☆545Updated 3 months ago
- A Distributed Attention Towards Linear Scalability for Ultra-Long Context, Heterogeneous Data Training☆385Updated this week
- Scalable and memory-optimized training of diffusion models☆1,189Updated 3 weeks ago
- (CVPR 2025) From Slow Bidirectional to Fast Autoregressive Video Diffusion Models☆651Updated last month
- MMaDA - Open-Sourced Multimodal Large Diffusion Language Models☆1,109Updated last week
- ☆731Updated this week
- [CVPR 2025 Oral]Infinity ∞ : Scaling Bitwise AutoRegressive Modeling for High-Resolution Image Synthesis☆1,341Updated this week
- A pipeline parallel training script for diffusion models.☆1,174Updated last week
- ☆283Updated 5 months ago
- Official repo for CFG-Zero*☆596Updated last month
- Fork of the Triton language and compiler for Windows support and easy installation☆1,067Updated this week
- https://wavespeed.ai/ Best inference performance optimization framework for HuggingFace Diffusers on NVIDIA GPUs.☆1,272Updated 2 months ago
- VideoSys: An easy and efficient system for video generation☆1,980Updated 3 months ago
- DFloat11: Lossless LLM Compression for Efficient GPU Inference☆426Updated last month
- A unified library of state-of-the-art model optimization techniques like quantization, pruning, distillation, speculative decoding, etc. …☆1,006Updated last week
- ☆622Updated 8 months ago
- 📚 Collection of awesome generation acceleration resources.☆270Updated 2 months ago
- A SOTA open-source image editing model, which aims to provide comparable performance against the closed-source models like GPT-4o and Gem…☆1,426Updated last week