#flash-attention (6 Repositories)
Ranked open-source repositories tagged with #flash-attention, scored by pull request acceptance likelihood and maintainer engagement velocity.
29.5%
0.0h
6 repositories tagged #flash-attention
NVIDIA/cudnn-frontend
cuDNN Frontend is NVIDIA's modern, open-source entry point to the cuDNN library and a growing collection of high-performance open-source kernels.
xlite-dev/ffpa-attn
Kernel Library for Large Headdim Attention (64~1024, BF16/FP8/FP4), 1.5x~15x↑ vs PyTorch SDPA.
HKUSTDial/flash-sparse-attention
Trainable fast and memory-efficient sparse attention
ot-triton-lab/flash-sinkhorn
The official repository of FlashSinkhorn [ICML 2026 Oral]
NVlabs/rcm
rCM & Causal-rCM: Leading and Unified Algorithms/Infrastructures for Bidirectional/Autoregressive Video Diffusion Distillation at Scale
Nathanw1014/strix-halo-llamacpp
Performance-tuned llama.cpp for AMD Strix Halo (gfx1151): FA + MoE-prefill fixes with a bundled current Mesa driver. Vulkan and HIP; portable dir, Docker, and distrobox.