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.
☆2,296Updated 3 weeks ago
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☆2,235Updated last month
- SpargeAttention: A training-free sparse attention that can accelerate any model inference.☆695Updated 2 weeks ago
- Model Compression Toolbox for Large Language Models and Diffusion Models☆607Updated 2 weeks ago
- Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model☆1,082Updated 2 months ago
- [ICLR2025 Spotlight] SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models☆2,794Updated this week
- A unified inference and post-training framework for accelerated video generation.☆2,108Updated this week
- https://wavespeed.ai/ Context parallel attention that accelerates DiT model inference with dynamic caching☆366Updated last month
- Fork of the Triton language and compiler for Windows support and easy installation☆1,327Updated this week
- 📚A curated list of Awesome Diffusion Inference Papers with Codes: Sampling, Cache, Quantization, Parallelism, etc.🎉☆380Updated last week
- [CVPR 2024 Highlight] DistriFusion: Distributed Parallel Inference for High-Resolution Diffusion Models☆702Updated 8 months ago
- Radial Attention Official Implementation☆485Updated 3 weeks ago
- Light Video Generation Inference Framework☆514Updated this week
- A Distributed Attention Towards Linear Scalability for Ultra-Long Context, Heterogeneous Data Training☆493Updated this week
- A pipeline parallel training script for diffusion models.☆1,490Updated this week
- Scalable and memory-optimized training of diffusion models☆1,259Updated 2 months ago
- https://wavespeed.ai/ Best inference performance optimization framework for HuggingFace Diffusers on NVIDIA GPUs.☆1,284Updated 5 months ago
- VideoSys: An easy and efficient system for video generation☆1,994Updated 3 weeks ago
- [CVPR 2024] DeepCache: Accelerating Diffusion Models for Free☆924Updated last year
- End-to-end recipes for optimizing diffusion models with torchao and diffusers (inference and FP8 training).☆377Updated 3 months ago
- [CVPR 2025 Oral]Infinity ∞ : Scaling Bitwise AutoRegressive Modeling for High-Resolution Image Synthesis☆1,417Updated 2 months ago
- [ICCV2025] From Reusing to Forecasting: Accelerating Diffusion Models with TaylorSeers☆269Updated 3 weeks ago
- Official repo for CFG-Zero*☆660Updated 3 months ago
- (CVPR 2025) From Slow Bidirectional to Fast Autoregressive Video Diffusion Models☆885Updated 3 weeks ago
- [ICML2025] Sparse VideoGen: Accelerating Video Diffusion Transformers with Spatial-Temporal Sparsity☆417Updated this week
- ☆1,033Updated this week
- Enhance-A-Video: Better Generated Video for Free☆567Updated 5 months ago
- DFloat11: Lossless LLM Compression for Efficient GPU Inference☆524Updated last week
- A SOTA open-source image editing model, which aims to provide comparable performance against the closed-source models like GPT-4o and Gem…☆1,603Updated last month
- ☆284Updated 8 months ago
- https://wavespeed.ai/ [WIP] The all in one inference optimization solution for ComfyUI, universal, flexible, and fast.☆1,141Updated 3 weeks ago