togethercomputer / flash-attention-3Links
Fast and memory-efficient exact attention
☆17Updated 8 months ago
Alternatives and similar repositories for flash-attention-3
Users that are interested in flash-attention-3 are comparing it to the libraries listed below
Sorting:
- [WIP] Better (FP8) attention for Hopper☆33Updated 6 months ago
- ☆74Updated 8 months ago
- (WIP) Parallel inference for black-forest-labs' FLUX model.☆19Updated 9 months ago
- QuIP quantization☆57Updated last year
- 🎬 3.7× faster video generation E2E 🖼️ 1.6× faster image generation E2E ⚡ ColumnSparseAttn 9.3× vs FlashAttn‑3 💨 ColumnSparseGEMM 2.5× …☆82Updated 2 months ago
- Making Flux go brrr on GPUs.☆131Updated last month
- [NeurIPS 2024] AsyncDiff: Parallelizing Diffusion Models by Asynchronous Denoising☆205Updated 6 months ago
- An auxiliary project analysis of the characteristics of KV in DiT Attention.☆32Updated 8 months ago
- A parallelism VAE avoids OOM for high resolution image generation☆75Updated 3 weeks ago
- ☆148Updated 2 months ago
- A WebUI for Side-by-Side Comparison of Media (Images/Videos) Across Multiple Folders☆23Updated 6 months ago
- faster parallel inference of mochi-1 video generation model☆125Updated 6 months ago
- Writing FLUX in Triton☆40Updated 11 months ago
- ☆173Updated 7 months ago
- The official implementation of PTQD: Accurate Post-Training Quantization for Diffusion Models☆100Updated last year
- ☆51Updated 2 months ago
- [ICML2025] LoRA fine-tune directly on the quantized models.☆35Updated 9 months ago
- Code for Draft Attention☆90Updated 3 months ago
- A Suite for Parallel Inference of Diffusion Transformers (DiTs) on multi-GPU Clusters☆47Updated last year
- PyTorch half precision gemm lib w/ fused optional bias + optional relu/gelu☆72Updated 8 months ago
- [ECCV24] MixDQ: Memory-Efficient Few-Step Text-to-Image Diffusion Models with Metric-Decoupled Mixed Precision Quantization☆44Updated 9 months ago
- FBI-LLM: Scaling Up Fully Binarized LLMs from Scratch via Autoregressive Distillation☆51Updated this week
- Implementation of SmoothCache, a project aimed at speeding-up Diffusion Transformer (DiT) based GenAI models with error-guided caching.☆45Updated last month
- Patch convolution to avoid large GPU memory usage of Conv2D☆92Updated 7 months ago
- Work in progress.☆72Updated last month
- https://wavespeed.ai/ Context parallel attention that accelerates DiT model inference with dynamic caching☆365Updated last month
- 🤗An Unified Cache Acceleration Toolbox for DiTs: Qwen-Image, Qwen-Image-Edit, FLUX.1, Wan2.1/2.2, etc.☆201Updated this week
- FastCache: Fast Caching for Diffusion Transformer Through Learnable Linear Approximation [Efficient ML Model]☆32Updated last week
- [ICLR 2025] FasterCache: Training-Free Video Diffusion Model Acceleration with High Quality☆244Updated 8 months ago
- [ECCV24] MixDQ: Memory-Efficient Few-Step Text-to-Image Diffusion Models with Metric-Decoupled Mixed Precision Quantization☆14Updated 9 months ago