thu-ml / SageAttentionLinks
[ICLR2025, ICML2025, NeurIPS2025 Spotlight] Quantized Attention achieves speedup of 2-5x compared to FlashAttention, without losing end-to-end metrics across language, image, and video models.
☆3,094Updated 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☆2,512Updated last week
- [ICML2025] SpargeAttention: A training-free sparse attention that accelerates any model inference.☆916Updated 3 weeks ago
- [ICLR2025 Spotlight] SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models☆3,632Updated this week
- Model Compression Toolbox for Large Language Models and Diffusion Models☆744Updated 5 months ago
- Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model☆1,235Updated 7 months ago
- A unified inference and post-training framework for accelerated video generation.☆3,002Updated this week
- Light Image Video Generation Inference Framework☆1,861Updated this week
- 🤗 A PyTorch-native and Flexible Inference Engine with Hybrid Cache Acceleration and Parallelism for DiTs.☆929Updated this week
- A pipeline parallel training script for diffusion models.☆1,812Updated last week
- Fork of the Triton language and compiler for Windows support and easy installation☆1,778Updated last week
- Qwen-Image-Lightning: Speed up Qwen-Image model with distillation☆1,192Updated 3 weeks ago
- https://wavespeed.ai/ Context parallel attention that accelerates DiT model inference with dynamic caching☆416Updated 6 months ago
- 📚A curated list of Awesome Diffusion Inference Papers with Codes: Sampling, Cache, Quantization, Parallelism, etc.🎉☆504Updated last week
- ☆1,646Updated this week
- TurboDiffusion: 100–200× Acceleration for Video Diffusion Models☆3,276Updated last week
- [NeurIPS 2025] Radial Attention: O(nlogn) Sparse Attention with Energy Decay for Long Video Generation☆575Updated 2 months ago
- Scalable and memory-optimized training of diffusion models☆1,327Updated 7 months ago
- [ICML2025, NeurIPS2025 Spotlight] Sparse VideoGen 1 & 2: Accelerating Video Diffusion Transformers with Sparse Attention☆621Updated last month
- [CVPR 2024 Highlight] DistriFusion: Distributed Parallel Inference for High-Resolution Diffusion Models☆718Updated last year
- (CVPR 2025) From Slow Bidirectional to Fast Autoregressive Video Diffusion Models☆1,181Updated 5 months ago
- [CVPR 2025 Oral]Infinity ∞ : Scaling Bitwise AutoRegressive Modeling for High-Resolution Image Synthesis☆1,540Updated 2 months ago
- https://wavespeed.ai/ Best inference performance optimization framework for HuggingFace Diffusers on NVIDIA GPUs.☆1,298Updated 10 months ago
- HunyuanImage-3.0: A Powerful Native Multimodal Model for Image Generation☆2,665Updated 2 months ago
- https://wavespeed.ai/ [WIP] The all in one inference optimization solution for ComfyUI, universal, flexible, and fast.☆1,206Updated 5 months ago
- A Distributed Attention Towards Linear Scalability for Ultra-Long Context, Heterogeneous Data Training☆622Updated this week
- 📹 A more flexible framework that can generate videos at any resolution and creates videos from images.☆1,843Updated this week
- End-to-end recipes for optimizing diffusion models with torchao and diffusers (inference and FP8 training).☆390Updated 3 weeks ago
- ☆1,427Updated last year
- Directly Aligning the Full Diffusion Trajectory with Fine-Grained Human Preference☆1,245Updated 3 months ago
- VideoSys: An easy and efficient system for video generation☆2,016Updated 5 months ago