[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.
☆3,449Jan 17, 2026Updated 5 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.☆1,008Feb 25, 2026Updated 4 months ago
- [ICLR2025 Spotlight] SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models☆3,900Mar 7, 2026Updated 4 months ago
- xDiT: A Scalable Inference Engine for Diffusion Transformers (DiTs) with Massive Parallelism☆2,647Updated this week
- Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model☆1,346Jun 8, 2025Updated last year
- FlashInfer: Kernel Library for LLM Serving☆5,896Updated this week
- GPUs on demand by Runpod - Special Offer Available • AdRun AI, ML, and HPC workloads on powerful cloud GPUs—without limits or wasted spend. Deploy GPUs in under a minute and pay by the second.
- A unified inference and post-training framework for accelerated video generation.☆3,799Updated this week
- Model Compression Toolbox for Large Language Models and Diffusion Models☆792Aug 14, 2025Updated 10 months ago
- Fork of the Triton language and compiler for Windows support and easy installation☆1,945Feb 18, 2026Updated 4 months ago
- ☆6,574May 24, 2026Updated last month
- ☆1,082Jul 12, 2025Updated 11 months ago
- https://wavespeed.ai/ Context parallel attention that accelerates DiT model inference with dynamic caching☆428Jul 5, 2025Updated last year
- [NeurIPS 2025] Radial Attention: O(nlogn) Sparse Attention with Energy Decay for Long Video Generation☆602Nov 11, 2025Updated 7 months ago
- Fast and memory-efficient exact attention☆24,304Jun 29, 2026Updated last week
- Distributed Compiler based on Triton for Parallel Systems☆1,476Jun 25, 2026Updated 2 weeks ago
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- https://wavespeed.ai/ [WIP] The all in one inference optimization solution for ComfyUI, universal, flexible, and fast.☆1,224Aug 2, 2025Updated 11 months ago
- [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Se…☆845Mar 6, 2025Updated last year
- ComfyUI Plugin of Nunchaku☆2,907Feb 19, 2026Updated 4 months ago
- A fast communication-overlapping library for tensor/expert parallelism on GPUs.☆1,332Aug 28, 2025Updated 10 months ago
- A sparse attention kernel supporting mix sparse patterns☆529Jan 18, 2026Updated 5 months ago
- [ICLR 2025] DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads☆538Feb 10, 2025Updated last year
- 🚀 Efficient implementations for emerging model architectures☆5,279Jun 30, 2026Updated last week
- FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.☆1,102Sep 4, 2024Updated last year
- A Distributed Attention Towards Linear Scalability for Ultra-Long Context, Heterogeneous Data Training☆865Updated this week
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- Quantized Attention on GPU☆44Nov 22, 2024Updated last year
- [ICML2025, NeurIPS2025 Spotlight] Sparse VideoGen 1 & 2: Accelerating Video Diffusion Transformers with Sparse Attention☆688Updated this week
- Tile primitives for speedy kernels☆3,516Jun 15, 2026Updated 3 weeks ago
- SLA: Beyond Sparsity in Diffusion Transformers via Fine-Tunable Sparse–Linear Attention☆318Feb 24, 2026Updated 4 months ago
- Official repo for CFG-Zero*☆706May 2, 2025Updated last year
- A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit and 4-bit floating point (FP8 and FP4) precision on H…☆3,411Updated this week
- GGUF Quantization support for native ComfyUI models☆3,811Jan 12, 2026Updated 5 months ago
- PyTorch native quantization and sparsity for training and inference☆2,886Updated this week
- Helpful tools and examples for working with flex-attention☆1,204Updated 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.
- Fork of SageAttention for Windows wheels and easy installation☆869Jun 20, 2026Updated 2 weeks ago
- ☆1,906Jun 23, 2026Updated 2 weeks ago
- Various custom nodes for ComfyUI☆2,807Jul 1, 2026Updated last week
- ☆2,597Aug 20, 2025Updated 10 months ago
- USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference☆675May 21, 2026Updated last month
- Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels☆6,592Updated this week
- [ICML 2025] XAttention: Block Sparse Attention with Antidiagonal Scoring☆279Jul 6, 2025Updated last year