Prebuilt SageAttention 2.2.0 wheel for RTX 5090/5080/5070 (Blackwell sm_120) with PyTorch 2.11 nightly and CUDA 12.8. ~35% faster diffusion sampling. Includes build instructions for the PyTorch header patch fix.
☆24Jan 28, 2026Updated 7 months ago
Alternatives and similar repositories for sageattention-blackwell
Users that are interested in sageattention-blackwell are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- This custom ComfyUI node, Find Perfect Resolution, calculates an optimal output resolution for an input image while preserving its aspect…☆25Dec 5, 2025Updated 9 months ago
- A visual prompt engineering toolkit for ComfyUI. Chain prompts together, see what fires, lock what works.☆29Jun 30, 2026Updated 2 months ago
- A set of Comfyui nodes☆18Sep 9, 2026Updated last week
- Fork of SpargeAttention (SparseSageAttention) for Windows wheels and easy installation☆40May 14, 2026Updated 4 months ago
- Workflow history for reference☆82Updated this week
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- Resource monitor for Nvidia within ComfyUI☆23May 4, 2026Updated 4 months ago
- https://github.com/thu-ml/SageAttention☆20Nov 5, 2025Updated 10 months ago
- Demo showing you calling ComfyUI API with ComfyDeploy☆20Aug 29, 2025Updated last year
- Flash Attention WHL Builds for Windows☆16May 30, 2025Updated last year
- Fast kernel library for Diffusion inference with multiple compute backends.☆222Updated this week
- ☆15Jul 23, 2025Updated last year
- Draw horizonat lines at pre-defined key levels for the day.☆10Aug 27, 2024Updated 2 years ago
- Utility for modders & mod users to help resolve conflicts between mods for The Witcher 3.☆11Mar 25, 2020Updated 6 years ago
- [ICLR2025, ICML2025, NeurIPS2025 Spotlight] Quantized Attention achieves speedup of 2-5x compared to FlashAttention, without losing end-t…☆80Jan 19, 2026Updated 8 months ago
- 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.
- Pre-compiled acceleration packages (xFormers, SageAttention, Flash Attention) for ComfyUI on Windows — NVIDIA RTX 5000 Series (Blackwell,…☆57May 13, 2026Updated 4 months ago
- Official implementation of the paper "TOKENTRIM: INFERENCE-TIME TOKEN PRUNING FOR AUTOREGRESSIVE LONG VIDEO GENERATION"☆15Feb 8, 2026Updated 7 months ago
- ☆26Jun 14, 2024Updated 2 years ago
- Comfyui运行高亮框样式选择节点，可单色，可渐变色。☆43Aug 7, 2026Updated last month
- The simplest way to bridge, swap, and on-ramp on ApeChain.☆28Apr 25, 2025Updated last year
- A batch file to install the latest ComfyUI, make a venv within it and automatically install Triton and SageAttention for Hunyaun etc work…☆67Oct 13, 2025Updated 11 months ago
- ☆14Sep 22, 2021Updated 4 years ago
- Testing things..☆38Aug 24, 2025Updated last year
- A skin smoothing filter to beautify faces.☆15Jan 18, 2021Updated 5 years ago
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- ☆17Oct 8, 2025Updated 11 months ago
- ☆15May 21, 2026Updated 3 months ago
- ☆11Jan 2, 2023Updated 3 years ago
- Build idbloader.img, trust.img, and uboot.img from compiled uboot☆10Feb 17, 2023Updated 3 years ago
- Audio Queue Services with Swift☆11Oct 6, 2016Updated 9 years ago
- MediaPipe is a cross-platform framework for building multimodal applied machine learning pipelines☆18Jul 26, 2020Updated 6 years ago
- ☆13Nov 17, 2022Updated 3 years ago
- Real-time 1:1 scale interactive video mosaic renderer☆16Dec 30, 2025Updated 8 months ago
- An extensive node suite for ComfyUI with over 210 new nodes☆229Jun 4, 2026Updated 3 months ago
- 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.
- Open-source transpiler for CUDA Tile (13.1) migration☆19Dec 9, 2025Updated 9 months ago
- Modification of the KSampler for running models like Wan2.2 a14B☆251Oct 22, 2025Updated 10 months ago
- ☆13May 25, 2023Updated 3 years ago
- Semi-direct Visual Odometry, modify to SVO2.0☆16Feb 1, 2018Updated 8 years ago
- Archived HavenDV fork; use ratbuddy/ratbuddyssey upstream.☆11Updated this week
- Unpacked resource files for easy editing with W3Edit; scripts; localization files☆16Aug 14, 2020Updated 6 years ago
- stable-diffusion-webui extension that bypass to lsmith☆11Apr 28, 2023Updated 3 years ago