[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.
☆3,999Jan 17, 2026Updated 9 months ago
Alternatives and similar repositories for SageAttention
Users that are interested in SageAttention are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- [ICML2025] SpargeAttention: A training-free sparse attention that accelerates any model inference.☆1,267Feb 25, 2026Updated 8 months ago
- [ICLR2025 Spotlight] SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models☆3,965Sep 6, 2026Updated 2 months ago
- SLA: Beyond Sparsity in Diffusion Transformers via Fine-Tunable Sparse–Linear Attention☆553Oct 18, 2026Updated 3 weeks ago
- TurboDiffusion: 100–200× Acceleration for Video Diffusion Models☆3,859Updated this week
- [NeurIPS 2025] Radial Attention: O(nlogn) Sparse Attention with Energy Decay for Long Video Generation☆609Nov 11, 2025Updated 11 months ago
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model☆1,388Jun 8, 2025Updated last year
- FlashInfer: Kernel Library for LLM Serving☆6,870Updated this week
- xDiT: A Scalable Inference Engine for Diffusion Transformers (DiTs) with Massive Parallelism☆2,750Updated this week
- A unified inference and post-training framework for accelerated video generation.☆4,790Updated this week
- [ICML2025, NeurIPS2025 Spotlight] Sparse VideoGen 1 & 2: Accelerating Video Diffusion Transformers with Sparse Attention☆713Jul 4, 2026Updated 4 months ago
- Lightweight Image Video Action Generation Inference Framework☆2,994Updated this week
- Fork of the Triton language and compiler for Windows support and easy installation☆1,950Feb 18, 2026Updated 8 months ago
- ☆6,812May 24, 2026Updated 5 months ago
- Fast and memory-efficient exact attention☆25,256Updated this week
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- Model Compression Toolbox for Large Language Models and Diffusion Models☆802Aug 14, 2025Updated last year
- Fork of SageAttention for Windows wheels and easy installation☆1,065Oct 9, 2026Updated 3 weeks ago
- A PyTorch-native inference engine with cache, parallelism, quantization and cpu offload for 100+ DiTs.☆1,302Updated this week
- Various custom nodes for ComfyUI☆3,458Oct 29, 2026Updated last week
- ComfyUI Plugin of Nunchaku☆2,931Sep 6, 2026Updated 2 months ago
- A Distributed Attention Towards Linear Scalability for Ultra-Long Context, Heterogeneous Data Training☆971Updated this week
- https://wavespeed.ai/ Context parallel attention that accelerates DiT model inference with dynamic caching☆436Jul 5, 2025Updated last year
- ☆1,095Jul 12, 2025Updated last year
- 🚀 Efficient implementations for emerging model architectures☆6,026Updated this week
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- Distributed Compiler and Optimized Parallel Kernels☆1,577Sep 18, 2026Updated last month
- A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit and 4-bit floating point (FP8 and FP4) precision on H…☆3,599Updated this week
- A Survey of Efficient Attention Methods: Hardware-efficient, Sparse, Compact, and Linear Attention☆314Dec 1, 2025Updated 11 months ago
- Tile primitives for speedy kernels☆3,795Sep 12, 2026Updated last month
- rCM & Causal-rCM: Leading and Unified Algorithms/Infrastructures for Bidirectional/Autoregressive Video Diffusion Distillation at Scale☆828Jun 25, 2026Updated 4 months ago
- [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Se…☆868Mar 6, 2025Updated last year
- GGUF Quantization support for native ComfyUI models☆4,235Jan 12, 2026Updated 9 months ago
- https://wavespeed.ai/ [WIP] The all in one inference optimization solution for ComfyUI, universal, flexible, and fast.☆1,235Aug 21, 2026Updated 2 months ago
- Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels☆8,924Updated this week
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- ☆1,380Updated this week
- FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.☆1,174Sep 4, 2024Updated 2 years ago
- A fast communication-overlapping library for tensor/expert parallelism on GPUs.☆1,376Aug 28, 2025Updated last year
- Hackable and optimized Transformers building blocks, supporting a composable construction.☆10,575Oct 29, 2026Updated last week
- DeepGEMM: clean and efficient BLAS kernel library on GPU☆9,170Oct 20, 2026Updated 2 weeks ago
- Wan: Open and Advanced Large-Scale Video Generative Models☆17,400Mar 5, 2026Updated 8 months ago
- CUDA Templates and Python DSLs for High-Performance Linear Algebra☆10,707Updated this week