[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.
☆3,296Jan 17, 2026Updated 3 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.☆976Feb 25, 2026Updated last month
- [ICLR2025 Spotlight] SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models☆3,799Mar 7, 2026Updated last month
- xDiT: A Scalable Inference Engine for Diffusion Transformers (DiTs) with Massive Parallelism☆2,597Apr 9, 2026Updated last week
- Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model☆1,305Jun 8, 2025Updated 10 months ago
- FlashInfer: Kernel Library for LLM Serving☆5,372Apr 11, 2026Updated last week
- Wordpress hosting with auto-scaling - Free Trial • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- A unified inference and post-training framework for accelerated video generation.☆3,396Updated this week
- Model Compression Toolbox for Large Language Models and Diffusion Models☆774Aug 14, 2025Updated 8 months ago
- Fork of the Triton language and compiler for Windows support and easy installation☆1,905Feb 18, 2026Updated 2 months ago
- ☆1,077Jul 12, 2025Updated 9 months ago
- ☆6,305Feb 22, 2026Updated last month
- https://wavespeed.ai/ Context parallel attention that accelerates DiT model inference with dynamic caching☆426Jul 5, 2025Updated 9 months ago
- [NeurIPS 2025] Radial Attention: O(nlogn) Sparse Attention with Energy Decay for Long Video Generation☆589Nov 11, 2025Updated 5 months ago
- Fast and memory-efficient exact attention☆23,344Updated this week
- Distributed Compiler based on Triton for Parallel Systems☆1,403Apr 10, 2026Updated last week
- Wordpress hosting with auto-scaling - Free Trial • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- https://wavespeed.ai/ [WIP] The all in one inference optimization solution for ComfyUI, universal, flexible, and fast.☆1,224Aug 2, 2025Updated 8 months ago
- [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Se…☆826Mar 6, 2025Updated last year
- ComfyUI Plugin of Nunchaku☆2,844Feb 19, 2026Updated 2 months ago
- A sparse attention kernel supporting mix sparse patterns☆497Jan 18, 2026Updated 3 months ago
- A fast communication-overlapping library for tensor/expert parallelism on GPUs.☆1,286Aug 28, 2025Updated 7 months ago
- [ICLR 2025] DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads☆536Feb 10, 2025Updated last year
- 🚀 Efficient implementations for emerging model architectures☆4,878Updated this week
- Quantized Attention on GPU☆44Nov 22, 2024Updated last year
- [ICML2025, NeurIPS2025 Spotlight] Sparse VideoGen 1 & 2: Accelerating Video Diffusion Transformers with Sparse Attention☆655Mar 6, 2026Updated last month
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.☆1,057Sep 4, 2024Updated last year
- SLA: Beyond Sparsity in Diffusion Transformers via Fine-Tunable Sparse–Linear Attention☆295Feb 24, 2026Updated last month
- Tile primitives for speedy kernels☆3,312Apr 8, 2026Updated last week
- Official repo for CFG-Zero*☆708May 2, 2025Updated 11 months ago
- A Distributed Attention Towards Linear Scalability for Ultra-Long Context, Heterogeneous Data Training☆781Apr 8, 2026Updated last week
- A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit and 4-bit floating point (FP8 and FP4) precision on H…☆3,280Updated this week
- GGUF Quantization support for native ComfyUI models☆3,478Jan 12, 2026Updated 3 months ago
- PyTorch native quantization and sparsity for training and inference☆2,786Updated this week
- Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels☆5,497Updated 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.
- Fork of SageAttention for Windows wheels and easy installation☆767Mar 25, 2026Updated 3 weeks ago
- Various custom nodes for ComfyUI☆2,506Updated this week
- Helpful tools and examples for working with flex-attention☆1,174Updated this week
- ☆2,588Aug 20, 2025Updated 7 months ago
- USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference☆664Jan 15, 2026Updated 3 months ago
- ☆1,792Updated this week
- [ICML 2025] XAttention: Block Sparse Attention with Antidiagonal Scoring☆277Jul 6, 2025Updated 9 months ago