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.
☆2,709Updated 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☆2,428Updated last week
- [ICLR2025 Spotlight] SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models☆3,381Updated last week
- [ICML2025] SpargeAttention: A training-free sparse attention that accelerates any model inference.☆785Updated last week
- Model Compression Toolbox for Large Language Models and Diffusion Models☆698Updated 3 months ago
- Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model☆1,172Updated 5 months ago
- A unified inference and post-training framework for accelerated video generation.☆2,659Updated this week
- Light Video Generation Inference Framework☆816Updated last week
- https://wavespeed.ai/ Context parallel attention that accelerates DiT model inference with dynamic caching☆388Updated 4 months ago
- A pipeline parallel training script for diffusion models.☆1,731Updated 2 weeks ago
- Fork of the Triton language and compiler for Windows support and easy installation☆1,583Updated last week
- 🤗A PyTorch-native Inference Engine with Hybrid Cache Acceleration and Parallelism for DiTs.☆588Updated this week
- 📚A curated list of Awesome Diffusion Inference Papers with Codes: Sampling, Cache, Quantization, Parallelism, etc.🎉☆447Updated 3 months ago
- Qwen-Image-Lightning: Speed up Qwen-Image model with distillation☆997Updated last month
- Scalable and memory-optimized training of diffusion models☆1,303Updated 5 months ago
- [NeurIPS 2025] Radial Attention: O(nlogn) Sparse Attention with Energy Decay for Long Video Generation☆558Updated 2 weeks ago
- ☆1,461Updated last week
- [CVPR 2024 Highlight] DistriFusion: Distributed Parallel Inference for High-Resolution Diffusion Models☆714Updated 11 months ago
- [CVPR 2024] DeepCache: Accelerating Diffusion Models for Free☆944Updated last year
- [ICML2025, NeurIPS2025 Spotlight] Sparse VideoGen 1 & 2: Accelerating Video Diffusion Transformers with Sparse Attention☆585Updated last week
- (CVPR 2025) From Slow Bidirectional to Fast Autoregressive Video Diffusion Models☆1,058Updated 3 months ago
- A Distributed Attention Towards Linear Scalability for Ultra-Long Context, Heterogeneous Data Training☆562Updated this week
- https://wavespeed.ai/ Best inference performance optimization framework for HuggingFace Diffusers on NVIDIA GPUs.☆1,291Updated 8 months ago
- [CVPR 2025 Oral]Infinity ∞ : Scaling Bitwise AutoRegressive Modeling for High-Resolution Image Synthesis☆1,503Updated 2 weeks ago
- 📹 A more flexible framework that can generate videos at any resolution and creates videos from images.☆1,550Updated 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…☆1,742Updated 2 months ago
- End-to-end recipes for optimizing diffusion models with torchao and diffusers (inference and FP8 training).☆385Updated 5 months ago
- [ICCV2025] From Reusing to Forecasting: Accelerating Diffusion Models with TaylorSeers☆334Updated 3 months ago
- Official repo for CFG-Zero*☆680Updated 6 months ago
- DFloat11: Lossless LLM Compression for Efficient GPU Inference☆562Updated this week
- https://wavespeed.ai/ [WIP] The all in one inference optimization solution for ComfyUI, universal, flexible, and fast.☆1,192Updated 3 months ago