Provide with pre-build flash-attention 2 and 3 package wheels on Linux and Windows using GitHub Actions
☆1,712Sep 3, 2026Updated this week
Alternatives and similar repositories for flash-attention-prebuild-wheels
Users that are interested in flash-attention-prebuild-wheels are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Pre-compiled Python whl for Flash-attention, SageAttention, NATTEN, xFormer etc☆852Aug 18, 2026Updated 2 weeks ago
- Fork of SageAttention for Windows wheels and easy installation☆1,028Updated this week
- Fork of the Triton language and compiler for Windows support and easy installation☆1,957Feb 18, 2026Updated 6 months ago
- Quantized Attention that achieves speedups of 2.1-3.1x and 2.7-5.1x compared to FlashAttention2 and xformers, respectively, without lossi…☆158Jul 9, 2026Updated last month
- Fork of SpargeAttention (SparseSageAttention) for Windows wheels and easy installation☆39May 14, 2026Updated 3 months ago
- AI Agents on DigitalOcean Gradient AI Platform • AdBuild production-ready AI agents using customizable tools or access multiple LLMs through a single endpoint. Create custom knowledge bases or connect external data.
- Pre-built wheels that erase Flash Attention 3 installation headaches.☆118Aug 17, 2026Updated 2 weeks ago
- Fast and memory-efficient exact attention☆942Dec 9, 2025Updated 8 months ago
- [ICLR2025, ICML2025, NeurIPS2025 Spotlight] Quantized Attention achieves speedup of 2-5x compared to FlashAttention, without losing end-t…☆3,703Jan 17, 2026Updated 7 months ago
- ☆2,015Updated this week
- Fast and memory-efficient exact attention☆24,839Updated this week
- ComfyUI Plugin of Nunchaku☆2,920Feb 19, 2026Updated 6 months ago
- Efficient Python bindings for the llama.cpp library☆525Updated this week
- Pre-compiled acceleration packages (xFormers, SageAttention, Flash Attention) for ComfyUI on Windows — NVIDIA RTX 5000 Series (Blackwell,…☆57May 13, 2026Updated 3 months ago
- verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework☆23,258Updated this week
- 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.
- [ICLR2025 Spotlight] SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models☆3,941Mar 7, 2026Updated 5 months ago
- Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.6, DeepSeek-V4, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL…☆15,506Updated this week
- Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.☆19,897Jan 30, 2026Updated 7 months ago
- A high-throughput and memory-efficient inference and serving engine for LLMs☆90,889Updated this week
- Triton with Windows support☆249Updated this week
- A pipeline parallel training script for diffusion models.☆2,013Aug 20, 2026Updated 2 weeks ago
- CUDA 12.8 accelerated prebuilt wheel of llama-cpp-python with full Gemma 3 model support for Windows 10/11 (x64). Built by boneylizard.☆17Aug 24, 2025Updated last year
- The ultimate training toolkit for finetuning diffusion models☆11,886Updated this week
- Fast kernel library for Diffusion inference with multiple compute backends.☆200Updated 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.
- 🚀 Efficient implementations for emerging model architectures☆5,689Updated this week
- CUDA Python wheels with PEP 503 index☆39Aug 20, 2026Updated 2 weeks ago
- Official SeedVR2 Video Upscaler for ComfyUI☆2,809Dec 24, 2025Updated 8 months ago
- ComfyUI-TBG-SAM3 A plug-and-play ComfyUI extension providing production-ready nodes for Meta’s SAM3 (Segment Anything Model 3) for text- …☆169Aug 2, 2026Updated last month
- EasyR1: An Efficient, Scalable, Multi-Modality RL Training Framework based on veRL☆5,144Updated this week
- Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model☆1,370Jun 8, 2025Updated last year
- FlashInfer: Kernel Library for LLM Serving☆6,326Updated this week
- High quality training free inpaint for every stable diffusion model. Supports ComfyUI☆1,374Aug 12, 2026Updated 3 weeks ago
- A PyTorch-native inference engine with cache, parallelism, quantization and cpu offload for DiTs.☆1,269Updated this week
- 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.
- ComfyUI-QwenVL custom node: Integrates the Qwen-VL series, including Qwen2.5-VL, Qwen3-VL, Qwen3.5-VL, Qwen3.6-VL (MoE), and Qwen3.8-VL, …☆872Updated this week
- SGLang is a high-performance serving framework for large language models and multimodal models.☆33,856Updated this week
- Open-source unified multimodal model☆6,165May 4, 2026Updated 4 months ago
- ☆1,297Updated this week
- ☆18Mar 14, 2026Updated 5 months ago
- [NeurIPS 2025] An official implementation of Flow-GRPO: Training Flow Matching Models via Online RL☆2,511May 7, 2026Updated 3 months ago
- slime is an LLM post-training framework for RL Scaling.☆8,368Updated this week