Fast and memory-efficient exact attention
☆944Dec 9, 2025Updated 10 months ago
Alternatives and similar repositories for flash-attention
Users that are interested in flash-attention are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Fork of the Triton language and compiler for Windows support and easy installation☆1,950Feb 18, 2026Updated 7 months ago
- Fast and memory-efficient exact attention - Windows wheels☆37Apr 30, 2025Updated last year
- Fork of SageAttention for Windows wheels and easy installation☆1,057Updated this week
- Pre-compiled Python whl for Flash-attention, SageAttention, NATTEN, xFormer etc☆876Sep 7, 2026Updated last month
- Fast and memory-efficient exact attention☆58Sep 21, 2026Updated 3 weeks ago
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- Quantized Attention that achieves speedups of 2.1-3.1x and 2.7-5.1x compared to FlashAttention2 and xformers, respectively, without lossi…☆158Sep 24, 2026Updated 2 weeks ago
- Windows compile of bitsandbytes for use in text-generation-webui.☆358Nov 18, 2023Updated 2 years ago
- Fast and memory-efficient exact attention☆25,115Updated this week
- ☆149Dec 14, 2025Updated 9 months ago
- ☆195Jul 31, 2024Updated 2 years ago
- [ICLR2025 Spotlight] SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models☆3,959Sep 6, 2026Updated last month
- A set of nodes for ComfyUI that can composite layer and mask to achieve Photoshop like functionality.☆3,183Updated this week
- GGUF Quantization support for native ComfyUI models☆4,148Jan 12, 2026Updated 8 months ago
- ☆467Oct 30, 2024Updated last year
- 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.
- Support for miscellaneous image models. Currently supports: DiT, PixArt, T5 and a few custom VAEs☆18May 20, 2024Updated 2 years ago
- This is a pre-built wheel of Triton 3.3.0 for Windows with Nvidia only + Proton☆44May 18, 2025Updated last year
- ComfyUI Plugin of Nunchaku☆2,932Sep 6, 2026Updated last month
- Diffusers wrapper to run Kwai-Kolors model☆592Oct 18, 2024Updated last year
- for tile the image for advanced control or modification☆1,042Sep 14, 2026Updated 3 weeks ago
- ☆6,730May 24, 2026Updated 4 months ago
- Support for miscellaneous image models. Currently supports: DiT, PixArt, HunYuanDiT, MiaoBi, and a few VAEs.☆536Dec 17, 2024Updated last year
- Various custom nodes for ComfyUI☆3,371Updated this week
- ☆110Dec 20, 2024Updated last year
- 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.
- [ICLR2025, ICML2025, NeurIPS2025 Spotlight] Quantized Attention achieves speedup of 2-5x compared to FlashAttention, without losing end-t…☆3,967Jan 17, 2026Updated 8 months ago
- ☆166Mar 19, 2025Updated last year
- ☆77Jul 18, 2026Updated 2 months ago
- Practice Code for text to image trainer☆557Feb 27, 2026Updated 7 months ago
- Inference Microsoft Florence2 VLM☆1,756May 6, 2026Updated 5 months ago
- ☆240May 22, 2024Updated 2 years ago
- ComfyUI Node☆725Jun 18, 2025Updated last year
- ComfyUI BrushNet nodes☆946Mar 31, 2025Updated last year
- ☆190Aug 30, 2026Updated last month
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- https://wavespeed.ai/ [WIP] The all in one inference optimization solution for ComfyUI, universal, flexible, and fast.☆1,238Aug 21, 2026Updated last month
- SUPIR upscaling wrapper for ComfyUI☆2,314Apr 29, 2026Updated 5 months ago
- Recommended based on comfyui node pictures:Joy_caption + MiniCPMv2_6-prompt-generator + florence2☆621Feb 6, 2025Updated last year
- This tool allows you to process multiple images simultaneously, including removing metadata and alpha channels from the images. / 本ツールは、複…☆11Dec 20, 2023Updated 2 years ago
- nunchaku0.3.0.dev2的各种轮子列表☆40May 20, 2025Updated last year
- ☆527Apr 26, 2025Updated last year
- ComfyUI nodes to use segment-anything-2☆1,222Sep 28, 2025Updated last year