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.
☆2,168Updated this 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☆2,172Updated 2 weeks ago
- SpargeAttention: A training-free sparse attention that can accelerate any model inference.☆670Updated last week
- [ICLR2025 Spotlight] SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models☆2,545Updated this week
- Model Compression Toolbox for Large Language Models and Diffusion Models☆578Updated 4 months ago
- Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model☆1,023Updated 2 months ago
- An unified inference and post-training framework for accelerated video generation.☆1,690Updated this week
- https://wavespeed.ai/ Context parallel attention that accelerates DiT model inference with dynamic caching☆350Updated last month
- Fork of the Triton language and compiler for Windows support and easy installation☆1,230Updated this week
- A Distributed Attention Towards Linear Scalability for Ultra-Long Context, Heterogeneous Data Training☆456Updated last week
- 📚A curated list of Awesome Diffusion Inference Papers with Codes: Sampling, Cache, Quantization, Parallelism, etc.🎉☆350Updated last week
- A pipeline parallel training script for diffusion models.☆1,347Updated this week
- [CVPR 2024 Highlight] DistriFusion: Distributed Parallel Inference for High-Resolution Diffusion Models☆699Updated 8 months ago
- Scalable and memory-optimized training of diffusion models☆1,243Updated 2 months ago
- Radial Attention Official Implementation☆470Updated this week
- [CVPR 2025 Oral]Infinity ∞ : Scaling Bitwise AutoRegressive Modeling for High-Resolution Image Synthesis☆1,393Updated last month
- [CVPR 2024] DeepCache: Accelerating Diffusion Models for Free☆914Updated last year
- https://wavespeed.ai/ Best inference performance optimization framework for HuggingFace Diffusers on NVIDIA GPUs.☆1,281Updated 4 months ago
- End-to-end recipes for optimizing diffusion models with torchao and diffusers (inference and FP8 training).☆372Updated 2 months ago
- Lumina-Image 2.0: A Unified and Efficient Image Generative Framework☆763Updated last month
- Light Video Generation Inference Framework☆366Updated this week
- ☆285Updated 7 months ago
- ☆841Updated this week
- (CVPR 2025) From Slow Bidirectional to Fast Autoregressive Video Diffusion Models☆836Updated 2 months ago
- [ICCV2025] From Reusing to Forecasting: Accelerating Diffusion Models with TaylorSeers☆245Updated last month
- Official repo for CFG-Zero*☆646Updated 3 months ago
- [ICML2025] Sparse VideoGen: Accelerating Video Diffusion Transformers with Spatial-Temporal Sparsity☆393Updated 2 months ago
- https://wavespeed.ai/ [WIP] The all in one inference optimization solution for ComfyUI, universal, flexible, and fast.☆1,111Updated this week
- VideoSys: An easy and efficient system for video generation☆1,992Updated 5 months ago
- Enhance-A-Video: Better Generated Video for Free☆563Updated 4 months ago
- Qwen-Image is a powerful image generation foundation model capable of complex text rendering and precise image editing.☆1,559Updated this week